arXiv subjects

Matthew Purver

Publications and source records attributed to Matthew Purver.

42 records · Page 3Linked to original sources

arXiv2020

How Furiously Can Colourless Green Ideas Sleep? Sentence Acceptability in Context

We study the influence of context on sentence acceptability. First we compare the acceptability ratings of sentences judged in isolation, with a relevant context, and with an irrelevant context. Our results show that context induces a cognitive load for humans, which compresses the distribution of ratings. Moreover, in relevant contexts we observe a discourse coherence effect which uniformly raises acceptability. Next, we test unidirectional and bidirectional language models in their ability to predict acceptability ratings. The bidirectional models show very promising results, with the best model achieving a new state-of-the-art for unsupervised acceptability prediction. The two sets of experiments provide insights into the cognitive aspects of sentence processing and central issues in the computational modelling of text and discourse.

cs.CL↗

arXiv2018

Exploring Semantic Incrementality with Dynamic Syntax and Vector Space Semantics

One of the fundamental requirements for models of semantic processing in dialogue is incrementality: a model must reflect how people interpret and generate language at least on a word-by-word basis, and handle phenomena such as fragments, incomplete and jointly-produced utterances. We show that the incremental word-by-word parsing process of Dynamic Syntax (DS) can be assigned a compositional distributional semantics, with the composition operator of DS corresponding to the general operation of tensor contraction from multilinear algebra. We provide abstract semantic decorations for the nodes of DS trees, in terms of vectors, tensors, and sums thereof; using the latter to model the underspecified elements crucial to assigning partial representations during incremental processing. As a working example, we give an instantiation of this theory using plausibility tensors of compositional distributional semantics, and show how our framework can incrementally assign a semantic plausibility measure as it parses phrases and sentences.

cs.CL↗

arXiv2016

Words, Concepts, and the Geometry of Analogy

This paper presents a geometric approach to the problem of modelling the relationship between words and concepts, focusing in particular on analogical phenomena in language and cognition. Grounded in recent theories regarding geometric conceptual spaces, we begin with an analysis of existing static distributional semantic models and move on to an exploration of a dynamic approach to using high dimensional spaces of word meaning to project subspaces where analogies can potentially be solved in an online, contextualised way. The crucial element of this analysis is the positioning of statistics in a geometric environment replete with opportunities for interpretation.

cs.CL↗

arXiv2014

Strongly Incremental Repair Detection

We present STIR (STrongly Incremental Repair detection), a system that detects speech repairs and edit terms on transcripts incrementally with minimal latency. STIR uses information-theoretic measures from n-gram models as its principal decision features in a pipeline of classifiers detecting the different stages of repairs. Results on the Switchboard disfluency tagged corpus show utterance-final accuracy on a par with state-of-the-art incremental repair detection methods, but with better incremental accuracy, faster time-to-detection and less computational overhead. We evaluate its performance using incremental metrics and propose new repair processing evaluation standards.

cs.CL↗

arXiv2014

Evaluating Neural Word Representations in Tensor-Based Compositional Settings

We provide a comparative study between neural word representations and traditional vector spaces based on co-occurrence counts, in a number of compositional tasks. We use three different semantic spaces and implement seven tensor-based compositional models, which we then test (together with simpler additive and multiplicative approaches) in tasks involving verb disambiguation and sentence similarity. To check their scalability, we additionally evaluate the spaces using simple compositional methods on larger-scale tasks with less constrained language: paraphrase detection and dialogue act tagging. In the more constrained tasks, co-occurrence vectors are competitive, although choice of compositional method is important; on the larger-scale tasks, they are outperformed by neural word embeddings, which show robust, stable performance across the tasks.

cs.CL↗

arXiv2013

Topic and Sentiment Analysis on OSNs: a Case Study of Advertising Strategies on Twitter

Social media have substantially altered the way brands and businesses advertise: Online Social Networks provide brands with more versatile and dynamic channels for advertisement than traditional media (e.g., TV and radio). Levels of engagement in such media are usually measured in terms of content adoption (e.g., likes and retweets) and sentiment, around a given topic. However, sentiment analysis and topic identification are both non-trivial tasks. In this paper, using data collected from Twitter as a case study, we analyze how engagement and sentiment in promoted content spread over a 10-day period. We find that promoted tweets lead to higher positive sentiment than promoted trends; although promoted trends pay off in response volume. We observe that levels of engagement for the brand and promoted content are highest on the first day of the campaign, and fall considerably thereafter. However, we show that these insights depend on the use of robust machine learning and natural language processing techniques to gather focused, relevant datasets, and to accurately gauge sentiment, rather than relying on the simple keyword- or frequency-based metrics sometimes used in social media research.

cs.SI↗