Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userFrom compositional semantics to Bayesian pragmatics via logical inference
من دلالات التركيبية إلى باغماتيكيات البيئي عبر الاستدلال المنطقي
350
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
توفر الدلالات الرسمية في تقليد مونتاجوفي صياغة معنى دقيقا، ولكن عادة دون نظرية رسمية من البراغماتية لمعايير السياق وحساستها لمعرفة الخلفية. وفي الوقت نفسه، تجعل النظريات الرسمية البراغماتية تنبؤات صريحة حول المعنى في السياق، ولكنها عموما دون دلالات تركيبية محددة جيدا. نقترح إطارا مشتركا للتفسير الدلالي والعملي للجمل في مواجهة المعرفة الاحتمالية. نحن نقوم بذلك (1) تمديد مخطط تفسير Montagovian لتوليد التوزيع عبر المعاني المحتملة، و (2) إنشاء خلفي لهذا التوزيع باستخدام متغير نماذج قانون الكلام الرشيد (RSA)، ولكن معمم على المقترحات التعسفية. يتم ربط هذه الجوانب من إطارنا معا من خلال تقييم الاستقصاء بموجب عدم اليقين الاحتمالي. نطبق نموذجنا على قرار أنشفورا وإظهار أنه يوفر تحيزات متوقعة بموجب افتراضات مناسبة حول توزيعات المعرفة المعجمية والعالمية. علاوة على ذلك، نلاحظ أن إخراج النموذج قوي للتغيرات في معاييرها داخل نطاقات معقولة.
Formal semantics in the Montagovian tradition provides precise meaning characterisations, but usually without a formal theory of the pragmatics of contextual parameters and their sensitivity to background knowledge. Meanwhile, formal pragmatic theories make explicit predictions about meaning in context, but generally without a well-defined compositional semantics. We propose a combined framework for the semantic and pragmatic interpretation of sentences in the face of probabilistic knowledge. We do so by (1) extending a Montagovian interpretation scheme to generate a distribution over possible meanings, and (2) generating a posterior for this distribution using a variant of the Rational Speech Act (RSA) models, but generalised to arbitrary propositions. These aspects of our framework are tied together by evaluating entailment under probabilistic uncertainty. We apply our model to anaphora resolution and show that it provides expected biases under suitable assumptions about the distributions of lexical and world-knowledge. Further, we observe that the model's output is robust to variations in its parameters within reasonable ranges.
References used
https://aclanthology.org/
rate research
Read More
Understanding spatial expressions and using them appropriately is necessary for seamless and natural human-machine interaction. However, capturing the semantics and appropriate usage of spatial prepositions is notoriously difficult, because of their
vagueness and polysemy. Although modern data-driven approaches are good at capturing statistical regularities in the usage, they usually require substantial sample sizes, often do not generalize well to unseen instances and, most importantly, their structure is essentially opaque to analysis, which makes diagnosing problems and understanding their reasoning process difficult. In this work, we discuss our attempt at modeling spatial senses of prepositions in English using a combination of rule-based and statistical learning approaches. Each preposition model is implemented as a tree where each node computes certain intuitive relations associated with the preposition, with the root computing the final value of the prepositional relation itself. The models operate on a set of artificial 3D room world'' environments, designed in Blender, taking the scene itself as an input. We also discuss our annotation framework used to collect human judgments employed in the model training. Both our factored models and black-box baseline models perform quite well, but the factored models will enable reasoned explanations of spatial relation judgements.
We propose a framework to model an operational conversational negation by applying worldly context (prior knowledge) to logical negation in compositional distributional semantics. Given a word, our framework can create its negation that is similar to
how humans perceive negation. The framework corrects logical negation to weight meanings closer in the entailment hierarchy more than meanings further apart. The proposed framework is flexible to accommodate different choices of logical negations, compositions, and worldly context generation. In particular, we propose and motivate a new logical negation using matrix inverse. We validate the sensibility of our conversational negation framework by performing experiments, leveraging density matrices to encode graded entailment information. We conclude that the combination of subtraction negation and phaser in the basis of the negated word yields the highest Pearson correlation of 0.635 with human ratings.
We investigate if a model can learn natural language with minimal linguistic input through interaction. Addressing this question, we design and implement an interactive language learning game that learns logical semantic representations compositional
ly. Our game allows us to explore the benefits of logical inference for natural language learning. Evaluation shows that the model can accurately narrow down potential logical representations for words over the course of the game, suggesting that our model is able to learn lexical mappings from scratch successfully.
We develop a novel approach for confidently accelerating inference in the large and expensive multilayer Transformers that are now ubiquitous in natural language processing (NLP). Amortized or approximate computational methods increase efficiency, bu
t can come with unpredictable performance costs. In this work, we present CATs -- Confident Adaptive Transformers -- in which we simultaneously increase computational efficiency, while guaranteeing a specifiable degree of consistency with the original model with high confidence. Our method trains additional prediction heads on top of intermediate layers, and dynamically decides when to stop allocating computational effort to each input using a meta consistency classifier. To calibrate our early prediction stopping rule, we formulate a unique extension of conformal prediction. We demonstrate the effectiveness of this approach on four classification and regression tasks.
Since the seminal work of Richard Montague in the 1970s, mathematical and logic tools have successfully been used to model several aspects of the meaning of natural language. However, visually impaired people continue to face serious difficulties in
getting full access to this important instrument. Our paper aims to present a work in progress whose main goal is to provide blind students and researchers with an adequate method to deal with the different resources that are used in formal semantics. In particular, we intend to adapt the Portuguese Braille system in order to accommodate the most common symbols and formulas used in this kind of approach and to develop pedagogical procedures to facilitate its learnability. By making this formalization compatible with the Braille coding (either traditional and electronic), we hope to help blind people to learn and use this notation, essential to acquire a better understanding of a great number of semantic properties displayed by natural language.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
