Natural Language Understanding: Instructions for (Present and Future) Use.
Roberto Navigli
- pp 5697-5702
Reads0
Chats0
TLDR
This paper looks at Natural Language Understanding, an area of Natural Language Processing aimed at making sense of text, through the lens of a visionary future: what do the authors expect a machine should be able to understand and what are the key dimensions that require the attention of researchers to make this dream come true?Abstract:
In this paper I look at Natural Language Understanding, an area of Natural Language Processing aimed at making sense of text, through the lens of a visionary future: what do we expect a machine should be able to understand? and what are the key dimensions that require the attention of researchers to make this dream come true?read more
Citations
More filters
Proceedings ArticleDOI
Breaking Through the 80% Glass Ceiling: Raising the State of the Art in Word Sense Disambiguation by Incorporating Knowledge Graph Information.
TL;DR: Enhanced WSD Integrating Synset Embeddings and Relations (EWISER), a neural supervised architecture that is able to tap into this wealth of knowledge by embedding information from the LKB graph within the neural architecture, and to exploit pretrained synset embeddings, enabling the network to predict synsets that are not in the training set.
Knowledge Graphs: New Directions for Knowledge Representation on the Semantic Web (Dagstuhl Seminar 18371)
TL;DR: This report documents the program and the outcomes of Dagstuhl Seminar 18371 "Knowledge Graphs: New Directions for Knowledge Representation on the Semantic Web", where a group of experts from academia and industry discussed fundamental questions around these topics for a week in early September 2018.
Proceedings ArticleDOI
With More Contexts Comes Better Performance: Contextualized Sense Embeddings for All-Round Word Sense Disambiguation
TL;DR: ARES representations enable a simple 1 Nearest-Neighbour algorithm to outperform state-of-the-art models, not only in the English Word Sense Disambiguation task, but also in the multilingual one, whilst training on sense-annotated data in English only.
Proceedings ArticleDOI
XL-AMR: Enabling Cross-Lingual AMR Parsing with Transfer Learning Techniques.
TL;DR: This work explores different transfer learning techniques for producing automatic AMR annotations across languages and develops a cross-lingual AMR parser, XL-AMR, which can be trained on the produced data and does not rely on AMR aligners or source-copy mechanisms.
Proceedings Article
One SPRING to Rule Them Both: Symmetric AMR Semantic Parsing and Generation without a Complex Pipeline
TL;DR: Sapienza et al. as mentioned in this paper cast text-to-AMR and AMR-toText generation as a symmetric transduction task and show that by devising a careful graph linearization and extending a pretrained encoder-decoder model, it is possible to obtain state-of-the-art performances in both tasks using the very same seq2seq approach.
References
More filters
A framework for representing knowledge
TL;DR: The authors describes frame systems as a formalism for representing knowledge and then concentrates on the issue of what the content of knowledge should be in specific domains, arguing that vision should be viewed symbolically with an emphasis on forming expectations and then using details to fill in slots in those expectations.
Journal ArticleDOI
Minds, brains, and programs
TL;DR: Only a machine could think, and only very special kinds of machines, namely brains and machines with internal causal powers equivalent to those of brains, and no program by itself is sufficient for thinking.
Proceedings ArticleDOI
Statistical phrase-based translation
TL;DR: The empirical results suggest that the highest levels of performance can be obtained through relatively simple means: heuristic learning of phrase translations from word-based alignments and lexical weighting of phrase translation.
Book
English Verb Classes and Alternations: A Preliminary Investigation
TL;DR: Levin this paper classified over 3,000 English verbs according to shared meaning and behavior, and examined verb behavior with respect to a wide range of syntactic alternations that reflect verb meaning.
Proceedings ArticleDOI
The Berkeley FrameNet Project
TL;DR: This report will present the project's goals and workflow, and information about the computational tools that have been adapted or created in-house for this work.