Share This Author
Language Models as Knowledge Bases?
An in-depth analysis of the relational knowledge already present (without fine-tuning) in a wide range of state-of-the-art pretrained language models finds that BERT contains relational knowledge competitive with traditional NLP methods that have some access to oracle knowledge.
Reasoning about Entailment with Neural Attention
- Tim Rocktäschel, Edward Grefenstette, K. Hermann, Tomás Kociský, P. Blunsom
- Computer ScienceICLR
- 22 September 2015
This paper proposes a neural model that reads two sentences to determine entailment using long short-term memory units and extends this model with a word-by-word neural attention mechanism that encourages reasoning over entailments of pairs of words and phrases, and presents a qualitative analysis of attention weights produced by this model.
Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
A general-purpose fine-tuning recipe for retrieval-augmented generation (RAG) -- models which combine pre-trained parametric and non-parametric memory for language generation, and finds that RAG models generate more specific, diverse and factual language than a state-of-the-art parametric-only seq2seq baseline.
e-SNLI: Natural Language Inference with Natural Language Explanations
- Oana-Maria Camburu, Tim Rocktäschel, Thomas Lukasiewicz, P. Blunsom
- Computer ScienceNeurIPS
- 4 December 2018
The Stanford Natural Language Inference dataset is extended with an additional layer of human-annotated natural language explanations of the entailment relations, which can be used for various goals, such as obtaining full sentence justifications of a model’s decisions, improving universal sentence representations and transferring to out-of-domain NLI datasets.
Stance Detection with Bidirectional Conditional Encoding
- Isabelle Augenstein, Tim Rocktäschel, Andreas Vlachos, Kalina Bontcheva
- Computer ScienceEMNLP
- 17 June 2016
Stance detection is the task of classifying the attitude expressed in a text towards a target such as Hillary Clinton to be "positive", negative" or "neutral". Previous work has assumed that either…
End-to-end Differentiable Proving
It is demonstrated that this architecture outperforms ComplEx, a state-of-the-art neural link prediction model, on three out of four benchmark knowledge bases while at the same time inducing interpretable function-free first-order logic rules.
Interpretation of Natural Language Rules in Conversational Machine Reading
This paper formalise this task and develops a crowd-sourcing strategy to collect 37k task instances based on real-world rules and crowd-generated questions and scenarios to assess its difficulty by evaluating the performance of rule-based and machine-learning baselines.
ChemSpot: a hybrid system for chemical named entity recognition
ChemSpot, a named entity recognition (NER) tool for identifying mentions of chemicals in natural language texts, including trivial names, drugs, abbreviations, molecular formulas and International Union of Pure and Applied Chemistry entities is presented.
RIDE: Rewarding Impact-Driven Exploration for Procedurally-Generated Environments
This work proposes a novel type of intrinsic reward which encourages the agent to take actions that lead to significant changes in its learned state representation and rewards the agent substantially more for interacting with objects that it can control.
DiCE: The Infinitely Differentiable Monte-Carlo Estimator
- Jakob N. Foerster, Gregory Farquhar, Maruan Al-Shedivat, Tim Rocktäschel, E. Xing, Shimon Whiteson
- Computer ScienceICML
- 12 February 2018
DiCE is introduced, which provides a single objective that can be differentiated repeatedly, generating correct gradient estimators of any order in SCGs, and is used to propose and evaluate a novel approach for multi-agent learning.