This paper presents FASTFOOD, a rule-based natural language generation (NLG) program for cooking recipes. We consider the representation of cooking recipes as discourse representation, because the meaning of each sentence needs to consider the context of the others. Our discourse representation system is based on states of affairs and transtions between states of affairs, and does not use discourse referents. Recipes are generated by using an automated theorem-proving procedure to select the ingredients and instructions, with ingredients corresponding to axioms and instructions to implications. FASTFOOD also contains a temporal optimization module which can rearrange the recipe to make it more time efficient for the user, e.g. the recipe specifies to chop the vegetables while the rice is boiling. The system is described in detail, including the decision to forgo discourse referents and how plausible representations of nouns and verbs emerge purely as a by-product of the practical requirements of efficiently representing recipe content. A comparison is then made with existing recipe generation systems, NLG systems more generally, and automated theorem provers.

This paper investigates the correlation between mutual gaze and linguistic repetition, a form of alignment, which we take as evidence of mutual understanding. We focus on a multimodal corpus made of three-party conversations and explore the question of whether mutual gaze events correspond to moments of repetition or non-repetition. Our results, although mainly significant on word unigrams and bigrams, suggest positive correlations between the presence of mutual gaze and the repetitions of tokens, lemmas, or parts-of-speech, but negative correlations when it comes to paired levels of representation (tokens or lemmas associated with their part-of-speech). No compelling correlation is found with duration of mutual gaze. Results are strongest when ignoring punctuation as representations of pauses, intonation, etc. in counting aligned tokens.

Cyberbullying discourse is achieved with multiple linguistic conveyances. Hyperboles witnessed in a corpus of cyberbullying utterances are studied. Linguistic features of hyperbole using the traditional grammatical indications of exaggerations are analyzed. The method relies on data selected from a larger corpus of utterances identified and labelled as “bullying”, from Twitter, from October 2020 to March 2022. An outcome is a lexicon of 250 entries. A small number of lexical level features have been isolated, and chi-squared contingency tests applied to evaluating their information value in identifying hyperbole. Words or affixes indicating superlatives or extremes of scales, with positive but not negative valency items, interact with hyperbole classification in this data set. All utterances extracted has been considered exaggerations and the stylistic status of “hyperbole” has been commented within the frame of new meanings in the context of social media.

This paper surveys 60 English Machine Reading Comprehension datasets, with a view to providing a convenient resource for other researchers interested in this problem. We categorize the datasets according to their question and answer form and compare them across various dimensions including size, vocabulary, data source, method of creation, human performance level, and first question word. Our analysis reveals that Wikipedia is by far the most common data source and that there is a relative lack of why, when, and where questions across datasets.

In this paper we explore the problem of machine reading comprehension, focusing on the BoolQ dataset of Yes/No questions. We carry out an error analysis of a BERT-based machine reading comprehension model on this dataset, revealing issues such as unstable model behaviour and some noise within the dataset itself. We then experiment with two approaches for integrating information from knowledge graphs: (i) concatenating knowledge graph triples to text passages and (ii) encoding knowledge with a Graph Neural Network. Neither of these approaches show a clear improvement and we hypothesize that this may be due to a combination of inaccuracies in the knowledge graph, imprecision in entity linking, and the models’ inability to capture additional information from knowledge graphs.

The task of Diachronic Word Sense Induction (DWSI) aims to identify the meaning of words from their context, taking the temporal dimension into account. In this paper we propose an evaluation method based on large-scale time-stamped annotated biomedical data, and a range of evaluation measures suited to the task. The approach is applied to two recent DWSI systems, thus demonstrating its relevance and providing an in-depth analysis of the models.

It has become commonplace for people to share their opinions about all kinds of products by posting reviews online. It has also become commonplace for potential customers to do research about the quality and limitations of these products by posting questions online. We test the extent to which reviews are useful in question-answering by combining two Amazon datasets and focusing our attention on yes/no questions. A manual analysis of 400 cases reveals that the reviews directly contain the answer to the question just over a third of the time. Preliminary reading comprehension experiments with this dataset prove inconclusive, with accuracy in the range 50-66%.

Tests added to Kleene algebra (by Kozen and others) are considered within Monadic Second Order logic over strings, where they are likened to statives in natural language. Reducts are formed over tests and non-tests alike, specifying what is observable. Notions of temporal granularity are based on observable change, under the assumption that a finite set bounds what is observable (with the possibility of stretching such bounds by moving to a larger finite set). String projections at different granularities are conjoined by superpositions that provide another variant of concatenation for Booleans.

This paper describes two systems for detecting Verbal Multiword Expressions (VMWEs) which both competed in the closed track at the PARSEME VMWE Shared Task 2018. CRF-DepTree-categs implements an approach based on the dependency tree, intended to exploit the syntactic and semantic relations between tokens; CRF-Seq-nocategs implements a robust sequential method which requires only lemmas and morphosyntactic tags. Both systems ranked in the top half of the ranking, the latter ranking second for token-based evaluation. The code for both systems is published under the GNU General Public License version 3.0 and is available at http://github.com/erwanm/adapt-vmwe18.

Casual conversation has become a focus for artificial dialogue applications. Such talk is ubiquitous and its structure differs from that found in the task-based interactions which have been the focus of dialogue system design for many years. It is unlikely that such conversations can be modelled as an extension of task-based talk. We review theories of casual conversation, report on our studies of the structure of casual dialogue, and outline challenges we see for the development of spoken dialog systems capable of carrying on casual friendly conversation in addition to performing well-defined tasks.

We describe the work of a team from the ADAPT Centre in Ireland in addressing automatic answer selection for the Multi-choice Question Answering in Examinations shared task. The system is based on a logistic regression over the string similarities between question, answer, and additional text. We obtain the highest grade out of six systems: 48.7% accuracy on a validation set (vs. a baseline of 29.45%) and 45.6% on a test set.

A description of a system for identifying Verbal Multi-Word Expressions (VMWEs) in running text is presented. The system mainly exploits universal syntactic dependency features through a Conditional Random Fields (CRF) sequence model. The system competed in the Closed Track at the PARSEME VMWE Shared Task 2017, ranking 2nd place in most languages on full VMWE-based evaluation and 1st in three languages on token-based evaluation. In addition, this paper presents an option to re-rank the 10 best CRF-predicted sequences via semantic vectors, boosting its scores above other systems in the competition. We also show that all systems in the competition would struggle to beat a simple lookup baseline system and argue for a more purpose-specific evaluation scheme.