Every word in the lexicon of a natural language is used distinctly from all the other words. A word expert is a small expert system-like module for processing a particular word based on other words in its vicinity. A word expert exploits the idiosyncratic nature of a word by using a set of context testing decision rules that test the identity and placement of context words to infer the word's role in the passage.

The main application of word experts is disambiguating words. Work on word experts has never fully recognized previous related work, and a comprehensive review of that work would therefore contribute to the field. This paper both provides such a review, and describes guidelines and considerations useful in the design and construction of word expert based systems.

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.

Large alphabet languages such as Chinese are very different from English, and therefore present different problems for text compression. In this article, we first examine the characteristics of Chinese, then we introduce a new variant of the Prediction by Partial Match (PPM) model especially for Chinese characters. Unlike the traditional PPM coding schemes, which encodes an escape probability if a novel character occurs in the context, the new coding scheme directly encodes the order first before encoding a symbol, without having to output an escape probability. This scheme achieves excellent compression rates in comparison with other schemes on a variety of Chinese text files.

This paper presents a classification-based approach to noun–noun compound interpretation within the statistical learning framework of kernel methods. In this framework, the primary modelling task is to define measures of similarity between data items, formalised as kernel functions. We consider the different sources of information that are useful for understanding compounds and proceed to define kernels that compute similarity between compounds in terms of these sources. In particular, these kernels implement intuitive notions of lexical and relational similarity and can be computed using distributional information extracted from text corpora. We report performance on classification experiments with three semantic relation inventories at different levels of granularity, demonstrating in each case that combining lexical and relational information sources is beneficial and gives better performance than either source taken alone. The data used in our experiments are taken from general English text, but our methods are also applicable to other domains and potentially to other languages where noun–noun compounding is frequent and productive.

Evaluation was not a thing when the first author was a graduate student in the late 1970s. There was an Artificial Intelligence (AI) boom then, but that boom was quickly followed by a bust and a long AI Winter. Charles Wayne restarted funding in the mid-1980s by emphasizing evaluation. No other sort of program could have been funded at the time, at least in America. His program was so successful that these days, shared tasks and leaderboards have become common place in speech and language (and Vision and Machine Learning). It is hard to remember that evaluation was a tough sell 25 years ago. That said, we may be a bit too satisfied with current state of the art. This paper will survey considerations from other fields such as reliability and validity from psychology and generalization from systems. There has been a trend for publications to report better and better numbers, but what do these numbers mean? Sometimes the numbers are too good to be true, and sometimes the truth is better than the numbers. It is one thing for an evaluation to fail to find a difference between man and machine, and quite another thing to pass the Turing Test. As Feynman said, “the first principle is that you must not fool yourself–and you are the easiest person to fool.”

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.

Roman Urdu is an informal form of the Urdu language written in Roman script, which is widely used in South Asia for online textual content. It lacks standard spelling and hence poses several normalization challenges during automatic language processing. In this article, we present a feature-based clustering framework for the lexical normalization of Roman Urdu corpora, which includes a phonetic algorithm UrduPhone, a string matching component, a feature-based similarity function, and a clustering algorithm Lex-Var. UrduPhone encodes Roman Urdu strings to their pronunciation-based representations. The string matching component handles character-level variations that occur when writing Urdu using Roman script. The similarity function incorporates various phonetic-based, string-based, and contextual features of words. The Lex-Var algorithm is a variant of the k-medoids clustering algorithm that groups lexical variations of words. It contains a similarity threshold to balance the number of clusters and their maximum similarity. The framework allows feature learning and optimization in addition to the use of predefined features and weights. We evaluate our framework extensively on four real-world datasets and show an F-measure gain of up to 15% from baseline methods. We also demonstrate the superiority of UrduPhone and Lex-Var in comparison to respective alternate algorithms in our clustering framework for the lexical normalization of Roman Urdu.

A text usually contains one or a few main topics, which are split up into subtopics, which in their turn can be further described by more detailed topics. In this article we describe a system that segments a text into topics and subtopics. Each segment is characterized by important key terms that are extracted from it and by its begin and end position in the text. A table of contents is built by using the hierarchical and sequential relationships between topical segments that are identified in a text. The table of contents generator relies upon universal linguistic theories on the topic and comment of a sentence and on patterns of thematic progression in text. The linguistic theories of topic and comment are modeled both deterministically and probabilistically. The system is applied to English texts (news, World Wide Web and encyclopedia texts) and is evaluated.

If you wanted to make some money out of natural language processing, an appropriate strategy might be to identify an area of technology that was relatively mature—one where the more fundamental technical problems had been resolved through a significant amount of research activity—and then identify potential applications for that technology.

Many English noun pairs suggest an almost limitless array of semantic interpretation. A fruit bowl might be described as a bowl for fruit, a bowl that contains fruit, a bowl for holding fruit, or even (perhaps in a modern sculpture class), a bowl made out of fruit. These interpretations vary in syntax, semantic denotation, plausibility, and level of semantic detail. For example, a headache pill is usually a pill for preventing headaches, but might, perhaps in the context of a list of side effects, be a pill that can cause headaches (Levi, J. N. 1978. The Syntax and Semantics of Complex Nominals. New York: Academic Press.). In addition to lexical ambiguity, both relational ambiguity and relational vagueness make automatic semantic interpretation of these combinations difficult. While humans parse these possibilities with ease, computational systems are only recently gaining the ability to deal with the complexity of lexical expressions of semantic relations. In this paper, we describe techniques for paraphrasing the semantic relations that can hold between nouns in a noun compound, using a semi-supervised probabilistic method to rank candidate paraphrases of semantic relations, and describing a new method for selecting plausible relational paraphrases at arbitrary levels of semantic specification. These methods are motivated by the observation that existing semantic relation classification schemes often exhibit a highly skewed class distribution, and that lexical paraphrases of semantic relations vary widely in semantic precision.

It’s no secret that the commercial application of NLP technologies has exploded in recent years. From chatbots and virtual assistants to machine translation and sentiment analysis, NLP technologies are now being used in a wide variety of applications across a range of industries. With the increasing demand for technologies that can process human language, investors have been eager to get a piece of the action. In this article, we look at NLP startup funding over the past year, identifying the applications and domains that have received investment.

Part-of-speech (PoS) tagging of non-standard language with models developed for standard language is known to suffer from a significant decrease in accuracy. Two methods are typically used to improve it: word normalisation, which decreases the out-of-vocabulary rate of the PoS tagger, and domain adaptation where the tagger is made aware of the non-standard language variation, either through supervision via non-standard data being added to the tagger’s training set, or via distributional information calculated from raw texts. This paper investigates the two approaches, normalisation and domain adaptation, on carefully constructed data sets encompassing historical and user-generated Slovene texts, in particular focusing on the amount of labour necessary to produce the manually annotated data sets for each approach and comparing the resulting PoS accuracy. We give quantitative as well as qualitative analyses of the tagger performance in various settings, showing that on our data set closed and open class words exhibit significantly different behaviours, and that even small inconsistencies in the PoS tags in the data have an impact on the accuracy. We also show that to improve tagging accuracy, it is best to concentrate on obtaining manually annotated normalisation training data for short annotation campaigns, while manually producing in-domain training sets for PoS tagging is better when a more substantial annotation campaign can be undertaken. Finally, unsupervised adaptation via Brown clustering is similarly useful regardless of the size of the training data available, but improvements tend to be bigger when adaptation is performed via in-domain tagging data.

Large language models (LLMs) have achieved amazing successes. They have done well on standardized tests in medicine and the law. That said, the bar has been raised so high that it could take decades to make good on expectations. To buy time for this long-term research program, the field needs to identify some good short-term applications for smooth-talking machines that are more fluent than trustworthy.

Abstractive summarization is an approach to document summarization that is not limited to selecting sentences from the document but can generate new sentences as well. We address the two main challenges in abstractive summarization: how to evaluate the performance of a summarization model and what is a good training objective. We first introduce new evaluation measures based on the semantic similarity of the input and corresponding summary. The similarity scores are obtained by the fine-tuned BERTurk model using either the cross-encoder or a bi-encoder architecture. The fine-tuning is done on the Turkish Natural Language Inference and Semantic Textual Similarity benchmark datasets. We show that these measures have better correlations with human evaluations compared to Recall-Oriented Understudy for Gisting Evaluation (ROUGE) scores and BERTScore. We then introduce a deep reinforcement learning algorithm that uses the proposed semantic similarity measures as rewards, together with a mixed training objective, in order to generate more natural summaries in terms of human readability. We show that training with a mixed training objective function compared to only the maximum-likelihood objective improves similarity scores.

This paper presents a general-purpose, wide-coverage, probabilistic sentence generator based on dependency n-gram models. This is particularly interesting as many semantic or abstract syntactic input specifications for sentence realisation can be represented as labelled bi-lexical dependencies or typed predicate-argument structures. Our generation method captures the mapping between semantic representations and surface forms by linearising a set of dependencies directly, rather than via the application of grammar rules as in more traditional chart-style or unification-based generators. In contrast to conventional n-gram language models over surface word forms, we exploit structural information and various linguistic features inherent in the dependency representations to constrain the generation space and improve the generation quality. A series of experiments shows that dependency-based n-gram models generalise well to different languages (English and Chinese) and representations (LFG and CoNLL). Compared with state-of-the-art generation systems, our general-purpose sentence realiser is highly competitive with the added advantages of being simple, fast, robust and accurate.

A growing body of recent work focuses on the challenging problem of scene understanding using a variety of cross-modal methods which fuse techniques from image and text processing. In this paper, we develop representations for the semantics of scenes by explicitly encoding the objects detected in them and their spatial relations. We represent image content via two well-known types of tree representations, namely constituents and dependencies. Our representations are created deterministically, can be applied to any image dataset irrespective of the task at hand, and are amenable to standard NLP tools developed for tree-based structures. We show that we can apply syntax-based SMT and tree kernel methods in order to build models for image description generation and image-based retrieval. Experimental results on real-world images demonstrate the effectiveness of the framework.

This paper presents a study about methods for normalization of historical texts. The aim of these methods is learning relations between historical and contemporary word forms. We have compiled training and test corpora for different languages and scenarios, and we have tried to read the results related to the features of the corpora and languages. Our proposed method, based on weighted finite-state transducers, is compared to previously published ones. Our method learns to map phonological changes using a noisy channel model; it is a simple solution that can use a limited amount of supervision in order to achieve adequate performance. The compiled corpora are ready to be used for other researchers in order to compare results. Concerning the amount of supervision for the task, we investigate how the size of training corpus affects the results and identify some interesting factors to anticipate the difficulty of the task.

Summarizing content contributed by individuals can be challenging, because people make different lexical choices even when describing the same events. However, there remains a significant need to summarize such content. Examples include the student responses to post-class reflective questions, product reviews, and news articles published by different news agencies related to the same events. High lexical diversity of these documents hinders the system’s ability to effectively identify salient content and reduce summary redundancy. In this paper, we overcome this issue by introducing an integer linear programming-based summarization framework. It incorporates a low-rank approximation to the sentence-word cooccurrence matrix to intrinsically group semantically similar lexical items. We conduct extensive experiments on datasets of student responses, product reviews, and news documents. Our approach compares favorably to a number of extractive baselines as well as a neural abstractive summarization system. The paper finally sheds light on when and why the proposed framework is effective at summarizing content with high lexical variety.

The growing availability of textual sources has lead to an increase in the use of automatic knowledge acquisition approaches from textual data, as in Information Extraction (IE). Most IE systems use knowledge explicitly represented as sets of IE rules usually manually acquired. Recently, however, the acquisition of this knowledge has been faced by applying a huge variety of Machine Learning (ML) techniques. Within this framework, new problems arise in relation to the way of selecting and annotating positive examples, and sometimes negative ones, in supervised approaches, or the way of organizing unsupervised or semi-supervised approaches. This paper presents a new IE-rule learning system that deals with these training set problems and describes a set of experiments for testing this capability of the new learning approach.