Learning and applying contextual constraints in sentence comprehension

John, Mark St.; McClelland, James L.

doi:10.1016/0004-3702(90)90008-n

Cited by 253 publications

(90 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…These fine-grained discriminations were crucial for the model's account of animacy effects in RC processing. These and other studies of distributional semantic effects in SRNs (Elman, 1990; St John and McClelland, 1990) show that there is potential for future work to incorporate other distributional “semantic” effects. There is also potential to make the distributions more natural, thereby capturing some additional ambiguity effects not in the present model.…”

Section: Discussionmentioning

confidence: 55%

“…An important feature of SRNs is that they generalize over their training experiences with individual sentences to find regularities across the training items (Elman, 1990; St John and McClelland, 1990). The results in Figure 1 reflect generalization in MacDonald and Christiansen's SRN—in that object and subject relatives were presented equally often but were not equally difficult, because the model generalized from simple transitive sentences to the similar subject relatives.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Experience and generalization in a connectionist model of Mandarin Chinese relative clause processing

Hsiao

MacDonald

2013

Front. Psychol.

View full text Add to dashboard Cite

Sentences containing relative clauses are well known to be difficult to comprehend, and they have long been an arena in which to investigate the role of working memory in language comprehension. However, recent work has suggested that relative clause processing is better described by ambiguity resolution processes than by limits on extrinsic working memory. We investigated these alternative views with a Simple Recurrent Network (SRN) model of relative clause processing in Mandarin Chinese, which has a unique pattern of word order across main and relative clauses and which has yielded mixed results in human comprehension studies. To assess the model's ability to generalize from similar sentence structures, and to observe effects of ambiguity through the sentence, we trained the model on several different sentence types, based on a detailed corpus analysis of Mandarin relative clauses and simple sentences, coded to include patterns of noun animacy in the various structures. The model was evaluated on 16 different relative clause subtypes. Its performance corresponded well to human reading times, including effects previously attributed to working memory overflow. The model's performance across a wide variety of sentence types suggested that the seemingly inconsistent results in some prior empirical studies stemmed from failures to consider the full range of sentence types in empirical studies. Crucially, sentence difficulty for the model was not simply a reflection of sentence frequency in the training set; the model generalized from similar sentences and showed high error rates at points of ambiguity. The results suggest that SRNs are a powerful tool to examine the complicated constraint-satisfaction process of sentence comprehension, and that understanding comprehension of specific structures must include consideration of experiences with other similar structures in the language.

show abstract

Section: Discussionmentioning

confidence: 55%

Section: Introductionmentioning

confidence: 99%

Experience and generalization in a connectionist model of Mandarin Chinese relative clause processing

Hsiao

MacDonald

2013

Front. Psychol.

View full text Add to dashboard Cite

show abstract

“…McClelland & Elman, 1986;Norris, 1994), speech production (e.g. Dell, 1986), thematic assignment (e.g., McClelland & Kawamoto, 1986;St John & McClelland, 1990) and aspects of language acquisition (Plunkett & Marchman, 1991;Rumelhart & McClelland, 1986).…”

Section: Introductionmentioning

confidence: 99%

Accounting for regressive eye-movements in models of sentence processing: A reappraisal of the Selective Reanalysis hypothesis

Mitchell

Shen

Green

et al. 2008

Journal of Memory and Language

125

View full text Add to dashboard Cite

“…In the discourse/text comprehension literature, by contrast, the focus has traditionally been on explaining mental model construction and representation (e.g., Golden & Rumelhart, 1993;Kintsch, 1988Kintsch, , 1998Kintsch, , 2001Myers & O'Brien, 1998;St. John & McClelland, 1990Langston & Trabasso, 1999;van den Broek, Risden, Fletcher, & Thurlow, 1996).…”

Section: Introductionmentioning

confidence: 99%

Expectation-based Comprehension: Modeling the Interaction of World Knowledge and Linguistic Experience

Venhuizen

Crocker

Brouwer

2018

Discourse Processes

View full text Add to dashboard Cite

The processing difficulty of each word we encounter in a sentence is affected by both our prior linguistic experience and our general knowledge about the world. Computational models of incremental language processing have, however, been limited in accounting for the influence of world knowledge. We develop an incremental model of language comprehension that constructs-on a word-by-word basis-rich, probabilistic situation model representations. To quantify linguistic processing effort, we adopt Surprisal Theory, which asserts that the processing difficulty incurred by a word is inversely proportional to its expectancy (Hale, 2001;Levy, 2008). In contrast with typical language model implementations of surprisal, the proposed model instantiates a novel comprehension-centric metric of surprisal that reflects the likelihood of the unfolding utterance meaning as established after processing each word. Simulations are presented that demonstrate that linguistic experience and world knowledge are integrated in the model at the level of interpretation and combine in determining online expectations.

show abstract

Learning and applying contextual constraints in sentence comprehension

Cited by 253 publications

References 9 publications

Experience and generalization in a connectionist model of Mandarin Chinese relative clause processing

Experience and generalization in a connectionist model of Mandarin Chinese relative clause processing

Accounting for regressive eye-movements in models of sentence processing: A reappraisal of the Selective Reanalysis hypothesis

Expectation-based Comprehension: Modeling the Interaction of World Knowledge and Linguistic Experience

Contact Info

Product

Resources

About