Interpreting Fine-Grained Categories from Natural Language Queries of Entity Search

2018 ◽  
pp. 861-877
Author(s):  
Denghao Ma ◽  
Yueguo Chen ◽  
Xiaoyong Du ◽  
Yuanzhe Hao
Keyword(s):  
Natural Language ◽  
Entity Search ◽  
Fine Grained

scholarly journals Datives with psych nouns and adjectives in Basque

2020 ◽  
Vol 54 (3) ◽  
pp. 647-696
Author(s):  
Beatriz Fernández ◽  
Fernando Zúñiga ◽  
Ane Berro
Keyword(s):  
Natural Language ◽  
Linguistic Theory ◽  
Psychological State ◽  
Formal Expression ◽  
Fine Grained ◽  
Psych Verbs ◽  
Other Regarding ◽  
Psychological Verbs

Abstract This paper explores the formal expression of two Basque dative argument types in combination with psych nouns and adjectives, in intransitive and transitive clauses: (i) those that express the experiencer, and (ii) those that express the stimulus of the psychological state denoted by the psych noun and adjective. In the intransitive structure involving a dative experiencer (DatExpIS), the stimulus is in the absolutive case, and the intransitive copula izan ‘be’ shows both dative and absolutive agreement. This construction basically corresponds to those built upon the piacere type of psychological verbs typified in (Belletti, Adriana & Luigi Rizzi. 1988. Psych-verbs and θ-theory. Natural Language and Linguistic Theory 6. 291–352) three-way classification of Italian psych verbs. In the intransitive structure involving a dative stimulus (DatStimIS), the experiencer is marked by absolutive case, and the same intransitive copula shows both absolutive and dative agreement (with the latter corresponding to the dative stimulus and not to the experiencer). We show that the behavior of the dative argument in the two constructions is just the opposite of each other regarding a number of morphosyntactic tests, including agreement, constituency, hierarchy and selection. Additionally, we explore two parallel transitive constructions that involve either a dative experiencer and an ergative stimulus (DatExpTS) or a dative stimulus and an ergative experiencer (DatStimTS), which employ the transitive copula *edun ‘have’. Considering these configurations, we propose an extended and more fine-grained typology of psych predicates.

scholarly journals Densely Supervised Hierarchical Policy-Value Network for Image Paragraph Generation

2019 ◽  
Author(s):  
Siying Wu ◽  
Zheng-Jun Zha ◽  
Zilei Wang ◽  
Houqiang Li ◽  
Feng Wu
Keyword(s):  
Natural Language ◽  
State Of The Art ◽  
Cross Entropy ◽  
Image Captioning ◽  
Value Network ◽  
Entropy Loss ◽  
Fine Grained ◽  
Performance Improvements ◽  
Single Sentence ◽  
Multiple State

Image paragraph generation aims to describe an image with a paragraph in natural language. Compared to image captioning with a single sentence, paragraph generation provides more expressive and fine-grained description for storytelling. Existing approaches mainly optimize paragraph generator towards minimizing word-wise cross entropy loss, which neglects linguistic hierarchy of paragraph and results in ``sparse" supervision for generator learning. In this paper, we propose a novel Densely Supervised Hierarchical Policy-Value (DHPV) network for effective paragraph generation. We design new hierarchical supervisions consisting of hierarchical rewards and values at both sentence and word levels. The joint exploration of hierarchical rewards and values provides dense supervision cues for learning effective paragraph generator. We propose a new hierarchical policy-value architecture which exploits compositionality at token-to-token and sentence-to-sentence levels simultaneously and can preserve the semantic and syntactic constituent integrity. Extensive experiments on the Stanford image-paragraph benchmark have demonstrated the effectiveness of the proposed DHPV approach with performance improvements over multiple state-of-the-art methods.

scholarly journals Datives with psych nouns and adjectives in Basque

2020 ◽  
Vol 0 (0) ◽  
Author(s):  
Beatriz Fernández ◽  
Fernando Zúñiga ◽  
Ane Berro
Keyword(s):  
Natural Language ◽  
Linguistic Theory ◽  
Psychological State ◽  
Formal Expression ◽  
Fine Grained ◽  
Psych Verbs ◽  
Other Regarding ◽  
Psychological Verbs

AbstractThis paper explores the formal expression of two Basque dative argument types in combination with psych nouns and adjectives, in intransitive and transitive clauses: (i) those that express the experiencer, and (ii) those that express the stimulus of the psychological state denoted by the psych noun and adjective. In the intransitive structure involving a dative experiencer (DatExpIS), the stimulus is in the absolutive case, and the intransitive copula izan ‘be’ shows both dative and absolutive agreement. This construction basically corresponds to those built upon the piacere type of psychological verbs typified in (Belletti, Adriana & Luigi Rizzi. 1988. Psych-verbs and θ-theory. Natural Language and Linguistic Theory 6. 291–352) three-way classification of Italian psych verbs. In the intransitive structure involving a dative stimulus (DatStimIS), the experiencer is marked by absolutive case, and the same intransitive copula shows both absolutive and dative agreement (with the latter corresponding to the dative stimulus and not to the experiencer). We show that the behavior of the dative argument in the two constructions is just the opposite of each other regarding a number of morphosyntactic tests, including agreement, constituency, hierarchy and selection. Additionally, we explore two parallel transitive constructions that involve either a dative experiencer and an ergative stimulus (DatExpTS) or a dative stimulus and an ergative experiencer (DatStimTS), which employ the transitive copula *edun ‘have’. Considering these configurations, we propose an extended and more fine-grained typology of psych predicates.

scholarly journals Specificity distinction

2001 ◽  
Vol 23 ◽  
pp. 85-101
Author(s):  
Donka F. Farkas
Keyword(s):  
Natural Language ◽  
Noun Phrase ◽  
Noun Phrases ◽  
Extensive Literature ◽  
Semantic Type ◽  
Fine Grained ◽  
Rich Variety ◽  
Different Types ◽  
The Rich ◽  
The Way

This paper is concerned with semantic noun phrase typology, focusing on the question of how to draw fine-grained distinctions necessary for an accurate account of natural language phenomena. In the extensive literature on this topic, the most commonly encountered parameters of classification concern the semantic type of the denotation of the noun phrase, the familiarity or novelty of its referent, the quantificational/nonquantificational distinction (connected to the weak/strong dichotomy), as well as, more recently, the question of whether the noun phrase is choice-functional or not (see Reinhart 1997, Winter 1997, Kratzer 1998, Matthewson 1999). In the discussion that follows I will attempt to make the following general points: (i) phenomena involving the behavior of noun phrases both within and across languages point to the need of establishing further distinctions that are too fine-grained to be caught in the net of these typologies; (ii) some of the relevant distinctions can be captured in terms of conditions on assignment functions; (iii) distribution and scopal peculiarities of noun phrases may result from constraints they impose on the way variables they introduce are to be assigned values. Section 2 reviews the typology of definite noun phrases introduced in Farkas 2000 and the way it provides support for the general points above. Section 3 examines some of the problems raised by recognizing the rich variety of 'indefinite' noun phrases found in natural language and by attempting to capture their distribution and interpretation. Common to the typologies discussed in the two sections is the issue of marking different types of variation in the interpretation of a noun phrase. In the light of this discussion, specificity turns out to be an epiphenomenon connected to a family of distinctions that are marked differently in different languages.  

Object localization based on natural language descriptions for fine-grained image

2020 ◽  
Author(s):  
Duan Lijuan ◽  
Liang Mingliang ◽  
Qing En ◽  
Qiao yuanhua ◽  
Miao Jun ◽  
...  
Keyword(s):  
Natural Language ◽  
Object Localization ◽  
Fine Grained

scholarly journals The meanings of perspectival verbs and their implications on the taxonomy of projective content/conventional implicature

2016 ◽  
Vol 26 ◽  
pp. 43 ◽  
Author(s):  
David Yoshikazu Oshima
Keyword(s):  
Natural Language ◽  
Conventional Implicature ◽  
Global Context ◽  
Fine Grained ◽  
Sentence Meaning ◽  
Multidimensional Representation ◽  
Language Meaning

This work discusses the  presuppositional meanings of three kinds of perspectival (perspective-sensitive) verbs: (i) motion-deictic verbs, (ii) empathy-loaded verbs, and (iii) referent-honorific verbs, and their implications on the taxonomy of "projective content", which subsumes but is not limited to presupposition. Building on Tonhauser, Beaver, Roberts & Simons's (2013; "Toward a taxonomy of projective content", Language 89) four-way classification of projective content, I propose a more fine-grained, six-way classification that distinguishes "global-context oriented" content, which obligatorily projects through a "filter" operator such as a belief predicate, and "ambioriented" content, which  optionally does so. I also develop a "pseudo-multidimensional" representation of natural language meaning, where (i) proffered content, (ii) nonpresuppositional projective content, and (iii) presuppositional projective content have distinct roles in the sentence meaning, while anaphoric interaction across them is nevertheless possible.

scholarly journals Can MOOC Instructor Be Portrayed by Semantic Features? Using Discourse and Clustering Analysis to Identify Lecture-Style of Instructors in MOOCs

2021 ◽  
Vol 12 ◽  
Author(s):  
Changcheng Wu ◽  
Junyi Li ◽  
Ye Zhang ◽  
Chunmei Lan ◽  
Kaiji Zhou ◽  
...  
Keyword(s):  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Semantic Analysis ◽  
Sentence Length ◽  
Semantic Features ◽  
Course Quality ◽  
Fine Grained ◽  
Massive Open Online Course ◽  
Complex Words

Nowadays, most courses in massive open online course (MOOC) platforms are xMOOCs, which are based on the traditional instruction-driven principle. Course lecture is still the key component of the course. Thus, analyzing lectures of the instructors of xMOOCs would be helpful to evaluate the course quality and provide feedback to instructors and researchers. The current study aimed to portray the lecture styles of instructors in MOOCs from the perspective of natural language processing. Specifically, 129 course transcripts were downloaded from two major MOOC platforms. Two semantic analysis tools (linguistic inquiry and word count and Coh-Metrix) were used to extract semantic features including self-reference, tone, effect, cognitive words, cohesion, complex words, and sentence length. On the basis of the comments of students, course video review, and the results of cluster analysis, we found four different lecture styles: “perfect,” “communicative,” “balanced,” and “serious.” Significant differences were found between the different lecture styles within different disciplines for notes taking, discussion posts, and overall course satisfaction. Future studies could use fine-grained log data to verify the results of our study and explore how to use the results of natural language processing to improve the lecture of instructors in both MOOCs and traditional classes.

scholarly journals Prediction as a Basis for Skilled Reading: Insights from Natural Language Engineering Models

2021 ◽  
Author(s):  
Benedetta Cevoli ◽  
Chris Watkins ◽  
Kathleen Rastle
Keyword(s):  
Natural Language ◽  
Eye Movement ◽  
Internal State ◽  
Movement Behaviour ◽  
Language Engineering ◽  
Fine Grained ◽  
Modern Natural ◽  
Language Research ◽  
Engineering Models ◽  
English Speaking

Reading is not an inborn human capability, and yet, English-speaking adults read with impressive speed. This study considered how predictions of upcoming words impact on this skilled behaviour. We used a powerful computer model from natural language engineering (GPT-2) to derive predictions of upcoming words in text passages. These predictions were highly accurate, and showed a tight relationship to fine-grained aspects of eye-movement behaviour when adults read those same passages, including whether to skip the next word and how long to spend on it. Strong predictions that did not materialise resulted in a prediction error cost on fixation durations. Our findings suggest that predictions for upcoming words can be made based on relatively superficial statistical information in reading, and that these predictions guide how our eyes interrogate text. This study is the first to demonstrate a relationship between the internal state of a modern natural language engineering model and eye-movement behaviour in reading, opening substantial new opportunities for language research and application.

Sign in / Sign up

Export Citation Format

Share Document