Proceedings of the Eight Workshop on Cognitive Aspects of Computational Language Learning and Processing
- Anthology ID:
- ACL | CogACLL | WS
- Association for Computational Linguistics
The task of taking a semantic representation of a noun and predicting the brain activity triggered by it in terms of fMRI spatial patterns was pioneered by Mitchell et al. 2008. That seminal work used word co-occurrence features to represent the meaning of the nouns. Even though the task does not impose any specific type of semantic representation, the vast majority of subsequent approaches resort to feature-based models or to semantic spaces (aka word embeddings). We address this task, with competitive results, by using instead a semantic network to encode lexical semantics, thus providing further evidence for the cognitive plausibility of this approach to model lexical meaning.
A number of different discourse connectives can be used to mark the same discourse relation, but it is unclear what factors affect connective choice. One recent account is the Rational Speech Acts theory, which predicts that speakers try to maximize the informativeness of an utterance such that the listener can interpret the intended meaning correctly. Existing prior work uses referential language games to test the rational account of speakers’ production of concrete meanings, such as identification of objects within a picture. Building on the same paradigm, we design a novel Discourse Continuation Game to investigate speakers’ production of abstract discourse relations. Experimental results reveal that speakers significantly prefer a more informative connective, in line with predictions of the RSA model.
We present an analysis of the internal mechanism of the recurrent neural model of sentence production presented by Calvillo et al. (2016). The results show clear patterns of computation related to each layer in the network allowing to infer an algorithmic account, where the semantics activates the semantically related words, then each word generated at each time step activates syntactic and semantic constraints on possible continuations, while the recurrence preserves information through time. We propose that such insights could generalize to other models with similar architecture, including some used in computational linguistics for language modeling, machine translation and image caption generation.
In recent years, a variety of recurrent neural networks have been proposed, e.g LSTM. However, existing models only read the text once, it cannot describe the situation of repeated reading in reading comprehension. In fact, when reading or analyzing a text, we may read the text several times rather than once if we couldn’t well understand it. So, how to model this kind of the reading behavior? To address the issue, we propose a multi-glance mechanism (MGM) for modeling the habit of reading behavior. In the proposed framework, the actual reading process can be fully simulated, and then the obtained information can be consistent with the task. Based on the multi-glance mechanism, we design two types of recurrent neural network models for repeated reading: Glance Cell Model (GCM) and Glance Gate Model (GGM). Visualization analysis of the GCM and the GGM demonstrates the effectiveness of multi-glance mechanisms. Experiments results on the large-scale datasets show that the proposed methods can achieve better performance.
This paper presents a statistical model to predict Japanese word order in the double object constructions. We employed a Bayesian linear mixed model with manually annotated predicate-argument structure data. The findings from the refined corpus analysis confirmed the effects of information status of an NP as ‘givennew ordering’ in addition to the effects of ‘long-before-short’ as a tendency of the general Japanese word order.
We present a novel methodology involving mappings between different modes of semantic representation. We propose distributional semantic models as a mechanism for representing the kind of world knowledge inherent in the system of abstract symbols characteristic of a sophisticated community of language users. Then, motivated by insight from ecological psychology, we describe a model approximating affordances, by which we mean a language learner’s direct perception of opportunities for action in an environment. We present a preliminary experiment involving mapping between these two representational modalities, and propose that our methodology can become the basis for a cognitively inspired model of grounded language learning.
We present two methods that improve the assessment of cognitive models. The first method is applicable to models computing average acceptability ratings. For these models, we propose an extension that simulates a full rating distribution (instead of average ratings) and allows generating individual ratings. Our second method enables Bayesian inference for models generating individual data. To this end, we propose to use the cross-match test (Rosenbaum, 2005) as a likelihood function. We exemplarily present both methods using cognitive models from the domain of spatial language use. For spatial language use, determining linguistic acceptability judgments of a spatial preposition for a depicted spatial relation is assumed to be a crucial process (Logan and Sadler, 1996). Existing models of this process compute an average acceptability rating. We extend the models and – based on existing data – show that the extended models allow extracting more information from the empirical data and yield more readily interpretable information about model successes and failures. Applying Bayesian inference, we find that model performance relies less on mechanisms of capturing geometrical aspects than on mapping the captured geometry to a rating interval.
The current study examined the role of syntactic structure during pronoun resolution. We correlated complexity measures derived by the syntax-sensitive Hobbs algorithm and a neural network model for pronoun resolution with brain activity of participants listening to an audiobook during fMRI recording. Compared to the neural network model, the Hobbs algorithm is associated with larger clusters of brain activation in a network including the left Broca’s area.
This paper presents a left-corner parser for minimalist grammars. The relation between the parser and the grammar is transparent in the sense that there is a very simple 1-1 correspondence between derivations and parses. Like left-corner context-free parsers, left-corner minimalist parsers can be non-terminating when the grammar has empty left corners, so an easily computed left-corner oracle is defined to restrict the search.