Search Results for author:
Found 22 papers, 13 papers with code
SIGMORPHON 2021 Shared Task on Morphological Reinflection: Generalization Across Languages
This year's iteration of the SIGMORPHON Shared Task on morphological reinflection focuses on typological diversity and cross-lingual variation of morphosyntactic features.
Post-hoc Reward Calibration: A Case Study on Length Bias
Central to this process is the reward model (RM), which translates human feedback into training signals for optimising LLM behaviour.
Cross-Lingual and Cross-Cultural Variation in Image Descriptions
Do speakers of different languages talk differently about what they see?
Probing the Emergence of Cross-lingual Alignment during LLM Training
Multilingual Large Language Models (LLMs) achieve remarkable levels of zero-shot cross-lingual transfer performance.
Spectral Editing of Activations for Large Language Model Alignment
Large language models (LLMs) often exhibit undesirable behaviours, such as generating untruthful or biased content.
On the Independence Assumption in Neurosymbolic Learning
Many such systems assume that the probabilities of the considered symbols are conditionally independent given the input to simplify learning and reasoning.
Dynamic Memory Compression: Retrofitting LLMs for Accelerated Inference
Transformers have emerged as the backbone of large language models (LLMs).
Fine-tuning Large Language Models with Sequential Instructions
Despite the success of existing instruction-tuned models, we find that they usually struggle to respond to queries with multiple instructions.
Scaling Sparse Fine-Tuning to Large Language Models
We experiment with instruction-tuning of LLMs on standard dataset mixtures, finding that SpIEL is often superior to popular parameter-efficient fine-tuning methods like LoRA (low-rank adaptation) in terms of performance and comparable in terms of run time.
Are Large Language Models Temporally Grounded?
Instead, we provide LLMs with textual narratives and probe them with respect to their common-sense knowledge of the structure and duration of events, their ability to order events along a timeline, and self-consistency within their temporal model (e. g., temporal relations such as after and before are mutually exclusive for any pair of events).
Detecting and Mitigating Hallucinations in Multilingual Summarisation
With the existing faithful metrics focusing on English, even measuring the extent of this phenomenon in cross-lingual settings is hard.
Elastic Weight Removal for Faithful and Abstractive Dialogue Generation
We evaluate our method -- using different variants of Flan-T5 as a backbone language model -- on multiple datasets for information-seeking dialogue generation and compare our method with state-of-the-art techniques for faithfulness, such as CTRL, Quark, DExperts, and Noisy Channel reranking.
Efficient Transformers with Dynamic Token Pooling
Transformers achieve unrivalled performance in modelling language, but remain inefficient in terms of memory and time complexity.
UniMorph 4.0: Universal Morphology
The project comprises two major thrusts: a language-independent feature schema for rich morphological annotation and a type-level resource of annotated data in diverse languages realizing that schema.
FaithDial: A Faithful Benchmark for Information-Seeking Dialogue
The goal of information-seeking dialogue is to respond to seeker queries with natural language utterances that are grounded on knowledge sources.
Combining Modular Skills in Multitask Learning
By jointly learning these and a task-skill allocation matrix, the network for each task is instantiated as the average of the parameters of active skills.
Crossing the Conversational Chasm: A Primer on Natural Language Processing for Multilingual Task-Oriented Dialogue Systems
We find that the most critical factor preventing the creation of truly multilingual ToD systems is the lack of datasets in most languages for both training and evaluation.
AM2iCo: Evaluating Word Meaning in Context across Low-Resource Languages with Adversarial Examples
In order to address these gaps, we present AM2iCo (Adversarial and Multilingual Meaning in Context), a wide-coverage cross-lingual and multilingual evaluation set; it aims to faithfully assess the ability of state-of-the-art (SotA) representation models to understand the identity of word meaning in cross-lingual contexts for 14 language pairs.
Verb Knowledge Injection for Multilingual Event Processing
We investigate whether injecting explicit information on verbs' semantic-syntactic behaviour improves the performance of LM-pretrained Transformers in event extraction tasks -- downstream tasks for which accurate verb processing is paramount.
Emergent Communication Pretraining for Few-Shot Machine Translation
On the other hand, this also provides an extrinsic evaluation protocol to probe the properties of emergent languages ex vitro.
SIGTYP 2020 Shared Task: Prediction of Typological Features
Typological knowledge bases (KBs) such as WALS (Dryer and Haspelmath, 2013) contain information about linguistic properties of the world's languages.
Parameter Space Factorization for Zero-Shot Learning across Tasks and Languages
In this work, we propose a Bayesian generative model for the space of neural parameters.
