scholarly journals Anaphora resolution without world knowledge

2003 ◽  
Vol 19 (1) ◽  
pp. 181-200 ◽  
Author(s):  
Vilson J. Leffa
Keyword(s):  
Language Processing ◽  
Expository Text ◽  
Internal Representation ◽  
Schema Theory ◽  
Anaphora Resolution ◽  
Semantic Features ◽  
World Knowledge ◽  
Semantic Constraints ◽  
Pronominal Anaphora ◽  
Sentence Subject

A typical problem in the resolution of pronominal anaphora is the presence of more than one candidate for the antecedent of the pronoun. Considering two English sentences like (1) "People buy expensive cars because they offer more status" and (2) "People buy expensive cars because they want more status" we can see that the two NPs "people" and "expensive cars", from a purely syntactic perspective, are both legitimate candidates as antecedents for the pronoun "they". This problem has been traditionally solved by using world knowledge (e.g. schema theory), where, through an internal representation of the world, we "know" that cars "offer" status and people "want" status. The assumption in this paper is that the use of world knowledge does not explain how the disambiguation process works and alternative explanations should be explored. Using a knowledge poor approach (explicit information from the text rather than implicit world knowledge) the study investigates to what extent syntactic and semantic constraints can be used to resolve anaphora. For this purpose, 1,400 examples of the word "they" were randomly selected from a corpus of 10,000,000 words of expository text in English. Antecedent candidates for each case were then analyzed and classified in terms of their syntactic functions in the sentence (subject, object, etc.) and semantic features (+ human, + animate, etc.). It was found that syntactic constraints resolved 85% of the cases. When combined with semantic constraints the resolution rate rose to 98%. The implications of the findings for Natural Language Processing are discussed.

Pronominal Anaphora Resolution on Spanish Text

2021 ◽  
pp. 309-326
Author(s):  
Alonso García ◽  
Martha Victoria González ◽  
Francisco López-Orozco ◽  
Lucero Zamora
Keyword(s):  
Spanish Text ◽  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Spanish Language ◽  
Online Version ◽  
Anaphora Resolution ◽  
Personal Pronouns ◽  
Technological Advances ◽  
Pronominal Anaphora

Recent technological advances have allowed the development of numerous natural language processing applications with which users frequently interact. When interacting with this type of application, users often search for the economy of words, which promotes the use of pronouns, thereby highlighting the well-known anaphora problem. This chapter describes a proposal to approach the pronominal anaphora for the Spanish language. A set of rules (based on the Eagle standard) was designed to identify the referents of personal pronouns through the structure of the grammatical tags of the words. The proposed algorithm uses the online Freeling service to perform tokenization and tagging tasks. The performance of the algorithm was compared with an online version of Freeling, and the proposed algorithm shows better performance.

Deep Structured Learning for Natural Language Processing

2021 ◽  
Vol 20 (3) ◽  
pp. 1-14
Author(s):  
Yong Li ◽  
Xiaojun Yang ◽  
Min Zuo ◽  
Qingyu Jin ◽  
Haisheng Li ◽  
...  
Keyword(s):  
Public Opinion ◽  
Food Safety ◽  
Language Processing ◽  
Early Warning ◽  
Conditional Random Field ◽  
Semantic Features ◽  
Related Sequence ◽  
The Public ◽  
Network Public Opinion

The real-time and dissemination characteristics of network information make net-mediated public opinion become more and more important food safety early warning resources, but the data of petabyte (PB) scale growth also bring great difficulties to the research and judgment of network public opinion, especially how to extract the event role of network public opinion from these data and analyze the sentiment tendency of public opinion comment. First, this article takes the public opinion of food safety network as the research point, and a BLSTM-CRF model for automatically marking the role of event is proposed by combining BLSTM and conditional random field organically. Second, the Attention mechanism based on vocabulary in the field of food safety is introduced, the distance-related sequence semantic features are extracted by BLSTM, and the emotional classification of sequence semantic features is realized by using CNN. A kind of Att-BLSTM-CNN model for the analysis of public opinion and emotional tendency in the field of food safety is proposed. Finally, based on the time series, this article combines the role extraction of food safety events and the analysis of emotional tendency and constructs a net-mediated public opinion early warning model in the field of food safety according to the heat of the event and the emotional intensity of the public to food safety public opinion events.

Crossover: a unified view

1998 ◽  
Vol 34 (1) ◽  
pp. 73-124 ◽  
Author(s):  
RUTH KEMPSON ◽  
DOV GABBAY
Keyword(s):  
Language Processing ◽  
Deductive System ◽  
Anaphora Resolution ◽  
Unified View ◽  
On Line

This paper informally outlines a Labelled Deductive System for on-line language processing. Interpretation of a string is modelled as a composite lexically driven process of type deduction over labelled premises forming locally discrete databases, with rules of database inference then dictating their mode of combination. The particular LDS methodology is illustrated by a unified account of the interaction of wh-dependency and anaphora resolution, the so-called ‘cross-over’ phenomenon, currently acknowledged to resist a unified explanation. The shift of perspective this analysis requires is that interpretation is defined as a proof structure for labelled deduction, and assignment of such structure to a string is a dynamic left-right process in which linearity considerations are ineliminable.

A WORD-BASED CHINESE LANGUAGE UNDERSTANDING SYSTEM

1988 ◽  
Vol 02 (01) ◽  
pp. 25-35
Author(s):  
TIAN-SHUN YAO
Keyword(s):  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Chinese Language ◽  
Computer Programs ◽  
World Knowledge ◽  
Knowledge Source ◽  
Language Understanding ◽  
Language Analysis ◽  
The World

With the word-based theory of natural language processing, a word-based Chinese language understanding system has been developed. In the light of psychological language analysis and the features of the Chinese language, this theory of natural language processing is presented with the description of the computer programs based on it. The heart of the system is to define a Total Information Dictionary and the World Knowledge Source used in the system. The purpose of this research is to develop a system which can understand not only Chinese sentences but also the whole text.

scholarly journals INVESTIGATING READING COMPREHENSION PROCESSES IN ESP EDUCATION

2021 ◽  
Vol 18 (49) ◽  
pp. 91-105
Author(s):  
Maja Stanojević Gocić ◽  
Keyword(s):  
Reading Comprehension ◽  
Text Comprehension ◽  
Strategic Behavior ◽  
Progress Monitoring ◽  
Text Processing ◽  
Main Idea ◽  
Schema Theory ◽  
Specific Information ◽  
World Knowledge ◽  
Specific Reading

Reading is regarded as a cognitive process of meaning construction, or an interactive process that comprises low-level processes of word recognition and high-level processing of ideas. Schema theory implies the meaning of а text is not embedded in the text itself; it is actually created in an active manner through interaction between the reader and the text, in which readers use their world knowledge to decode text meaning. Accordingly, readers bring their ideas, experience and previously gained knowledge into reading comprehension processes. The attainment of specific reading goals, including main idea comprehension and extracting specific information from the text, requires the employment of various reading strategies. In that sense, strategic behavior is deployed by proficient readers; it enables them to facilitate and improve text comprehension, which is the ultimate aim of the reading skill. 10 ESP students of the College of Applied Professional Studies in Vranje took part in this research as respondents. After completing their reading comprehension assignments, students reported on those tasks by virtue of think-aloud protocols. This type of research may provide an insight into specific problems students encounter during text processing activities, as well as strategies they employ to resolve them, which would facilitate the evaluation of reading performance and progress monitoring. The results imply that strategic training would enable ESP students to efficiently attain both general and specific reading goals.

scholarly journals Be Relevant, Non-Redundant, and Timely: Deep Reinforcement Learning for Real-Time Event Summarization

2020 ◽  
Vol 34 (05) ◽  
pp. 9410-9417
Author(s):  
Min Yang ◽  
Chengming Li ◽  
Fei Sun ◽  
Zhou Zhao ◽  
Ying Shen ◽  
...  
Keyword(s):  
Reinforcement Learning ◽  
Real Time ◽  
Language Processing ◽  
Semantic Features ◽  
Unified Framework ◽  
Time Step ◽  
Dynamic Memory ◽  
The Arts ◽  
Real World Datasets ◽  
Event Summarization

Real-time event summarization is an essential task in natural language processing and information retrieval areas. Despite the progress of previous work, generating relevant, non-redundant, and timely event summaries remains challenging in practice. In this paper, we propose a Deep Reinforcement learning framework for real-time Event Summarization (DRES), which shows promising performance for resolving all three challenges (i.e., relevance, non-redundancy, timeliness) in a unified framework. Specifically, we (i) devise a hierarchical cross-attention network with intra- and inter-document attentions to integrate important semantic features within and between the query and input document for better text matching. In addition, relevance prediction is leveraged as an auxiliary task to strengthen the document modeling and help to extract relevant documents; (ii) propose a multi-topic dynamic memory network to capture the sequential patterns of different topics belonging to the event of interest and temporally memorize the input facts from the evolving document stream, avoiding extracting redundant information at each time step; (iii) consider both historical dependencies and future uncertainty of the document stream for generating relevant and timely summaries by exploiting the reinforcement learning technique. Experimental results on two real-world datasets have demonstrated the advantages of DRES model with significant improvement in generating relevant, non-redundant, and timely event summaries against the state-of-the-arts.

Multi-neural network-based sentiment analysis of food reviews based on character and word embeddings

2020 ◽  
pp. 002072092092849
Author(s):  
Yong Li ◽  
Qingyu Jin ◽  
Min Zuo ◽  
Haisheng Li ◽  
Xiaojun Yang ◽  
...  
Keyword(s):  
Neural Network ◽  
Sentiment Analysis ◽  
Language Processing ◽  
Chinese Character ◽  
Semantic Features ◽  
Word Embeddings ◽  
Emotional Information ◽  
Related Sequence ◽  
Active Research ◽  
Multi Neural Network

Sentiment analysis becomes one of the most active research hotspots in the field of natural language processing tasks in recent years. However, the inability to fully and effectively use emotional information is a problem in present deep learning models. A single Chinese character has different meanings in different words, and the character embeddings are combined with the word embeddings to extract more precise meaning information. In this paper, a single Chinese character and word are used as input units to train. Based on BLSTM, the attention mechanism based on vocabulary semantics in food field is introduced to realize distance-related sequence semantic feature extraction. CNN is used to realize semantic sentiment classification of sequence semantic features. Therefore, a model based on multi-neural network for sentiment information extraction and analysis is proposed. Experiments show that the model has excellent characteristics in sentiment analysis and obtains high accuracy and F value.

Sign in / Sign up

Export Citation Format

Share Document