The Processing Implementation of Syntactic Constraints: The Sentence Matching Debate

1992 ◽  
pp. 419-443
Author(s):  
Laurie A. Stowe
Keyword(s):  
Syntactic Constraints ◽  
Sentence Matching

Gated Convolutional Neural Network for Sentence Matching

2018 ◽  
Author(s):  
Peixin Chen ◽  
Wu Guo ◽  
Zhi Chen ◽  
Jian Sun ◽  
Lanhua You
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Sentence Matching

A Functional Explanation of French Nonlexical Datives

1985 ◽  
Vol 9 (2) ◽  
pp. 159-195 ◽  
Author(s):  
Betsy K. Barnes
Keyword(s):  
Functional Analysis ◽  
Functional Explanation ◽  
Semantic Constraints ◽  
Syntactic Constraints

The unity of French lexical and nonlexical uses of the dative clitic is made apparent by a functional analysis according to which the dative clitic always represents a 'theme' of the sentence, where thematicity is defined as greater relative saliency based on certain purely semantic (not pragmatic) properties and relations of arguments. The operation of certain semantic constraints on the nonlexical datives, which may be very approximately summarized as requiring that the dative complement be animate and that it be somehow affected by the act denoted by the rest of the VP, follows naturally, in accord with Dik's Markedness Hypothesis (Dik (1978)), from the view that the nonlexical datives represent a 'thematization' of an element which is otherwise (in alternative nondative constructions) represented as peripheral to the described event. The more limited occurrence of á-NP in nonlexical dative environments is explained by reference to general syntactic constraints on the language, together with the fact that à-NP, unlike the dative clitic, tends to be interpreted as an argument of V.

Sentence matching and well-formedness

Cognition ◽  
1987 ◽  
Vol 26 (2) ◽  
pp. 171-186 ◽  
Author(s):  
K.I. Forster ◽  
B.J. Stevenson
Keyword(s):  
Sentence Matching

scholarly journals DRr-Net: Dynamic Re-Read Network for Sentence Semantic Matching

2019 ◽  
Vol 33 ◽  
pp. 7442-7449 ◽  
Author(s):  
Kun Zhang ◽  
Guangyi Lv ◽  
Linyuan Wang ◽  
Le Wu ◽  
Enhong Chen ◽  
...  
Keyword(s):  
Natural Language ◽  
Small Region ◽  
Psychological Research ◽  
Attention Mechanism ◽  
Semantic Relations ◽  
Semantic Matching ◽  
Close Attention ◽  
Original Sentence ◽  
Benchmark Datasets ◽  
Sentence Matching

Sentence semantic matching requires an agent to determine the semantic relation between two sentences, which is widely used in various natural language tasks such as Natural Language Inference (NLI) and Paraphrase Identification (PI). Among all matching methods, attention mechanism plays an important role in capturing the semantic relations and properly aligning the elements of two sentences. Previous methods utilized attention mechanism to select important parts of sentences at one time. However, the important parts of the sentence during semantic matching are dynamically changing with the degree of sentence understanding. Selecting the important parts at one time may be insufficient for semantic understanding. To this end, we propose a Dynamic Re-read Network (DRr-Net) approach for sentence semantic matching, which is able to pay close attention to a small region of sentences at each step and re-read the important words for better sentence semantic understanding. To be specific, we first employ Attention Stack-GRU (ASG) unit to model the original sentence repeatedly and preserve all the information from bottom-most word embedding input to up-most recurrent output. Second, we utilize Dynamic Re-read (DRr) unit to pay close attention to one important word at one time with the consideration of learned information and re-read the important words for better sentence semantic understanding. Extensive experiments on three sentence matching benchmark datasets demonstrate that DRr-Net has the ability to model sentence semantic more precisely and significantly improve the performance of sentence semantic matching. In addition, it is very interesting that some of finding in our experiments are consistent with the findings of psychological research.

Adversarial Cross-domain Community Question Retrieval

2022 ◽  
Vol 21 (3) ◽  
pp. 1-22
Author(s):  
Aibo Guo ◽  
Xinyi Li ◽  
Ning Pang ◽  
Xiang Zhao
Keyword(s):  
Social Media ◽  
Information Sharing ◽  
Information Access ◽  
Professional Knowledge ◽  
Feature Space ◽  
Online Information ◽  
Cross Domain ◽  
Adversarial Training ◽  
Sentence Matching ◽  
Target Data

Community Q&A forum is a special type of social media that provides a platform to raise questions and to answer them (both by forum participants), to facilitate online information sharing. Currently, community Q&A forums in professional domains have attracted a large number of users by offering professional knowledge. To support information access and save users’ efforts of raising new questions, they usually come with a question retrieval function, which retrieves similar existing questions (and their answers) to a user’s query. However, it can be difficult for community Q&A forums to cover all domains, especially those emerging lately with little labeled data but great discrepancy from existing domains. We refer to this scenario as cross-domain question retrieval. To handle the unique challenges of cross-domain question retrieval, we design a model based on adversarial training, namely, X-QR , which consists of two modules—a domain discriminator and a sentence matcher. The domain discriminator aims at aligning the source and target data distributions and unifying the feature space by domain-adversarial training. With the assistance of the domain discriminator, the sentence matcher is able to learn domain-consistent knowledge for the final matching prediction. To the best of our knowledge, this work is among the first to investigate the domain adaption problem of sentence matching for community Q&A forums question retrieval. The experiment results suggest that the proposed X-QR model offers better performance than conventional sentence matching methods in accomplishing cross-domain community Q&A tasks.

Sign in / Sign up

Export Citation Format

Share Document