Text readability assessment is a challenging interdisciplinary endeavor with rich practical implications. It has long drawn the attention of researchers internationally, and the readability models since developed have been widely applied to various fields. Previous readability models have only made use of linguistic features employed for general text analysis and have not been sufficiently accurate when used to gauge domain-specific texts. In view of this, this study proposes a latent-semantic-analysis (LSA)-constructed hierarchical conceptual space that can be used to train a readability model to accurately assess domain-specific texts. Compared with a baseline reference using a traditional model, the new model improves by 13.88% to achieve 68.98% of accuracy when leveling social science texts, and by 24.61% to achieve 73.96% of accuracy when assessing natural science texts. We then combine the readability features developed for the current study with general linguistic features, and the accuracy of leveling social science texts improves by an even higher degree of 31.58% to achieve 86.68%, and that of natural science texts by 26.56% to achieve 75.91%. These results indicate that the readability features developed in this study can be used both to train a readability model for leveling domain-specific texts and also in combination with the more common linguistic features to enhance the efficacy of the model. Future research can expand the generalizability of the model by assessing texts from different fields and grade levels using the proposed method, thus enhancing the practical applications of this new method.

This paper serves as a short overview of the JNLE special issue on representation of the meaning of the sentence, bringing together traditional symbolic and modern continuous approaches. We indicate notable aspects of sentence meaning and their compatibility with the two streams of research and then summarize the papers selected for this special issue.

In this work, we focus on the task of open-type relation argument extraction (ORAE): given a corpus, a query entity Q, and a knowledge base relation (e.g., “Q authored notable work with title X”), the model has to extract an argument of non-standard entity type (entities that cannot be extracted by a standard named entity tagger, for example, X: the title of a book or a work of art) from the corpus. We develop and compare a wide range of neural models for this task yielding large improvements over a strong baseline obtained with a neural question answering system. The impact of different sentence encoding architectures and answer extraction methods is systematically compared. An encoder based on gated recurrent units combined with a conditional random fields tagger yields the best results. We release a data set to train and evaluate ORAE, based on Wikidata and obtained by distant supervision.

Natural Language Engineering really came about from a meeting between Roberto Garigliano (then of Durham University) and myself in his office in late 1992 or early 1993. I had returned to academia the previous year after a spell doing a variety of jobs in industry, and had become aware of Roberto and the Natural Language Group at Durham (just about 15 miles from the University of Sunderland where I was working). Roberto and I discussed several possible avenues of cooperation, including sponsorship by Durham of students on existing Sunderland masters degrees, a joint Durham/Sunderland specialist Masters in Language Engineering (which came to nothing) and a new journal focused on practical, engineering work in the language domain. Incidentally, one of the sponsored master’s students was Siobhan Devlin, now Head of Computing at Sunderland.

Cross-language information retrieval (CLIR), finding information in one language in response to queries expressed in another language, has attracted much attention due to the explosive growth of multilingual information in the World Wide Web. One important issue in CLIR is how to apply monolingual information retrieval (IR) methods in cross-lingual environments. Recently, learning to rank (LTR) approach has been successfully employed in different IR tasks. In this paper, we use LTR for CLIR. In order to adapt monolingual LTR techniques in CLIR and pass the barrier of language difference, we map monolingual IR features to CLIR ones using translation information extracted from different translation resources. The performance of CLIR is highly dependent on the size and quality of available bilingual resources. Effective use of available resources is especially important in low-resource language pairs. In this paper, we further propose an LTR-based method for combining translation resources in CLIR. We have studied the effectiveness of the proposed approach using different translation resources. Our results also show that LTR can be used to successfully combine different translation resources to improve the CLIR performance. In the best scenario, the LTR-based combination method improves the performance of single-resource-based CLIR method by 6% in terms of Mean Average Precision.

This article describes an unsupervised language model (LM) adaptation approach that can be used to enhance the performance of language identification methods. The approach is applied to a current version of the HeLI language identification method, which is now called HeLI 2.0. We describe the HeLI 2.0 method in detail. The resulting system is evaluated using the datasets from the German dialect identification and Indo-Aryan language identification shared tasks of the VarDial workshops 2017 and 2018. The new approach with LM adaptation provides considerably higher F1-scores than the basic HeLI or HeLI 2.0 methods or the other systems which participated in the shared tasks. The results indicate that unsupervised LM adaptation should be considered as an option in all language identification tasks, especially in those where encountering out-of-domain data is likely.

We analyze resources and models for Arabic community Question Answering (cQA). In particular, we focus on CQA-MD, our cQA corpus for Arabic in the domain of medical forums. We describe the corpus and the main challenges it poses due to its mix of informal and formal language, and of different Arabic dialects, as well as due to its medical nature. We further present a shared task on cQA at SemEval, the International Workshop on Semantic Evaluation, based on this corpus. We discuss the features and the machine learning approaches used by the teams who participated in the task, with focus on the models that exploit syntactic information using convolutional tree kernels and neural word embeddings. We further analyze and extend the outcome of the SemEval challenge by training a meta-classifier combining the output of several systems. This allows us to compare different features and different learning algorithms in an indirect way. Finally, we analyze the most frequent errors common to all approaches, categorizing them into prototypical cases, and zooming into the way syntactic information in tree kernel approaches can help solve some of the most difficult cases. We believe that our analysis and the lessons learned from the process of corpus creation as well as from the shared task analysis will be helpful for future research on Arabic cQA.

Unlike English and other Western languages, many Asian languages such as Chinese and Japanese do not delimit words by space. Word segmentation and new word detection are therefore key steps in processing these languages. Chinese word segmentation can be considered as a part-of-speech (POS)-tagging problem. We can segment corpus by assigning a label for each character which indicates the position of the character in a word (e.g., “B” for word beginning, and “E” for the end of the word, etc.). Chinese word segmentation seems to be well studied. Machine learning models such as conditional random field (CRF) and bi-directional long short-term memory (LSTM) have shown outstanding performances on this task. However, the segmentation accuracies drop significantly when applying the same approaches to out-domain cases, in which high-quality in-domain training data are not available. An example of out-domain applications is the new word detection in Chinese microblogs for which the availability of high-quality corpus is limited. In this paper, we focus on out-domain Chinese new word detection. We first design a new method Edge Likelihood (EL) for Chinese word boundary detection. Then we propose a domain-independent Chinese new word detector (DICND); each Chinese character is represented as a low-dimensional vector in the proposed framework, and segmentation-related features of the character are used as the values in the vector.

Information extraction is the process of converting unstructured text into a structured data base containing selected information from the text. It is an essential step in making the information content of the text usable for further processing. In this paper, we describe how information extraction has changed over the past 25 years, moving from hand-coded rules to neural networks, with a few stops on the way. We connect these changes to research advances in NLP and to the evaluations organized by the US Government.

We present two studies on neural network architectures that learn to represent sentences by composing their words according to automatically induced binary trees, without ever being shown a correct parse tree. We use Tree-Long Short-Term Memories (LSTMs) as our composition function, applied along a tree structure found by a differentiable natural language chart parser. The models simultaneously optimise both the composition function and the parser, thus eliminating the need for externally provided parse trees, which are normally required for Tree-LSTMs. They can therefore be seen as tree-based recurrent neural networks that are unsupervised with respect to the parse trees. Due to being fully differentiable, the models are easily trained with an off-the-shelf gradient descent method and backpropagation.

In the first part of this paper, we introduce a model based on the CKY chart parser, and evaluate its downstream performance on a natural language inference task and a reverse dictionary task. Further, we show how its performance can be improved with an attention mechanism which fully exploits the parse chart, by attending over all possible subspans of the sentence. We find that our approach is competitive against similar models of comparable size and outperforms Tree-LSTMs that use trees produced by a parser.

Finally, we present an alternative architecture based on a shift-reduce parser. We perform an analysis of the trees induced by both our models, to investigate whether they are consistent with each other and across re-runs, and whether they resemble the trees produced by a standard parser.

Irony and sarcasm are two complex linguistic phenomena that are widely used in everyday language and especially over the social media, but they represent two serious issues for automated text understanding. Many labeled corpora have been extracted from several sources to accomplish this task, and it seems that sarcasm is conveyed in different ways for different domains. Nonetheless, very little work has been done for comparing different methods among the available corpora. Furthermore, usually, each author collects and uses their own datasets to evaluate his own method. In this paper, we show that sarcasm detection can be tackled by applying classical machine-learning algorithms to input texts sub-symbolically represented in a Latent Semantic space. The main consequence is that our studies establish both reference datasets and baselines for the sarcasm detection problem that could serve the scientific community to test newly proposed methods.

This work focuses on the rapid development of linguistic annotation tools for low-resource languages (languages that have no labeled training data). We experiment with several cross-lingual annotation projection methods using recurrent neural networks (RNN) models. The distinctive feature of our approach is that our multilingual word representation requires only a parallel corpus between source and target languages. More precisely, our approach has the following characteristics: (a) it does not use word alignment information, (b) it does not assume any knowledge about target languages (one requirement is that the two languages (source and target) are not too syntactically divergent), which makes it applicable to a wide range of low-resource languages, (c) it provides authentic multilingual taggers (one tagger for N languages). We investigate both uni and bidirectional RNN models and propose a method to include external information (for instance, low-level information from part-of-speech tags) in the RNN to train higher level taggers (for instance, Super Sense taggers). We demonstrate the validity and genericity of our model by using parallel corpora (obtained by manual or automatic translation). Our experiments are conducted to induce cross-lingual part-of-speech and Super Sense taggers. We also use our approach in a weakly supervised context, and it shows an excellent potential for very low-resource settings (less than 1k training utterances).

Text normalization is the task of mapping noncanonical language, typical of speech transcription and computer-mediated communication, to a standardized writing. This task is especially important for languages such as Swiss German, with strong regional variation and no written standard. In this paper, we propose a novel solution for normalizing Swiss German WhatsApp messages using the encoder–decoder neural machine translation (NMT) framework. We enhance the performance of a plain character-level NMT model with the integration of a word-level language model and linguistic features in the form of part-of-speech (POS) tags. The two components are intended to improve the performance by addressing two specific issues: the former is intended to improve the fluency of the predicted sequences, whereas the latter aims at resolving cases of word-level ambiguity. Our systematic comparison shows that our proposed solution results in an improvement over a plain NMT system and also over a comparable character-level statistical machine translation system, considered the state of the art in this task till recently. We perform a thorough analysis of the compared systems’ output, showing that our two components produce indeed the intended, complementary improvements.

Over the last two decades, determining the similarity between words as well as between their meanings, that is, word senses, has been proven to be of vital importance in the field of Natural Language Processing. This paper provides the reader with an introduction to the tasks of computing word and sense similarity. These consist in computing the degree of semantic likeness between words and senses, respectively. First, we distinguish between two major approaches: the knowledge-based approaches and the distributional approaches. Second, we detail the representations and measures employed for computing similarity. We then illustrate the evaluation settings available in the literature and, finally, discuss suggestions for future research.

Current approaches to learning semantic representations of sentences often use prior word-level knowledge. The current study aims to leverage visual information in order to capture sentence level semantics without the need for word embeddings. We use a multimodal sentence encoder trained on a corpus of images with matching text captions to produce visually grounded sentence embeddings. Deep Neural Networks are trained to map the two modalities to a common embedding space such that for an image the corresponding caption can be retrieved and vice versa. We show that our model achieves results comparable to the current state of the art on two popular image-caption retrieval benchmark datasets: Microsoft Common Objects in Context (MSCOCO) and Flickr8k. We evaluate the semantic content of the resulting sentence embeddings using the data from the Semantic Textual Similarity (STS) benchmark task and show that the multimodal embeddings correlate well with human semantic similarity judgements. The system achieves state-of-the-art results on several of these benchmarks, which shows that a system trained solely on multimodal data, without assuming any word representations, is able to capture sentence level semantics. Importantly, this result shows that we do not need prior knowledge of lexical level semantics in order to model sentence level semantics. These findings demonstrate the importance of visual information in semantics.

Approaches to building temporal information extraction systems typically rely on large, manually annotated corpora. Thus, porting these systems to new languages requires acquiring large corpora of manually annotated documents in the new languages. Acquiring such corpora is difficult owing to the complexity of temporal information extraction annotation. One strategy for addressing this difficulty is to reduce or eliminate the need for manually annotated corpora through annotation projection. This technique utilizes a temporal information extraction system for a source language (typically English) to automatically annotate the source language side of a parallel corpus. It then uses automatically generated word alignments to project the annotations, thereby creating noisily annotated target language training data. We developed an annotation projection technique for producing target language temporal information extraction systems. We carried out an English (source) to French (target) case study wherein we compared a French temporal information extraction system built using annotation projection with one built using a manually annotated French corpus. While annotation projection has been applied to building other kinds of Natural Language Processing tools (e.g., Named Entity Recognizers), to our knowledge, this is the first paper examining annotation projection as applied to temporal information extraction where no manual corrections of the target language annotations were made. We found that, even using manually annotated data to build a temporal information extraction system, F-scores were relatively low (<0.35), which suggests that the problem is challenging even with manually annotated data. Our annotation projection approach performed well (relative to the system built from manually annotated data) on some aspects of temporal information extraction (e.g., event–document creation time temporal relation prediction), but it performed poorly on the other kinds of temporal relation prediction (e.g., event–event and event–time).

In this paper, we provide an overview of research on multiword expressions (MWEs), from a natural language processing perspective. We examine methods developed for modelling MWEs that capture some of their linguistic properties, discussing their use for MWE discovery and for idiomaticity detection. We concentrate on their collocational and contextual preferences, along with their fixedness in terms of canonical forms and their lack of word-for-word translatatibility. We also discuss a sample of the MWE resources that have been used in intrinsic evaluation setups for these methods.

Nowadays, there is an increasing amount of digital data. In the case of the Web, daily, a vast collection of data is generated, whose contents are heterogeneous. A significant portion of this data is available in a natural language format. Open Information Extraction (Open IE) enables the extraction of facts from large quantities of texts written in natural language. In this work, we propose an Open IE method to extract facts from texts written in Portuguese. We developed two new rules that generalize the inference by transitivity and by symmetry. Consequently, this approach increases the number of implicit facts in a sentence. Our novel symmetric inference approach is based on a list of symmetric features. Our results confirmed that our method outstands close works both in precision and number of valid extractions. Considering the number of minimal facts, our approach is equivalent to the most relevant methods in the literature.