Related papers: Uncertainty-Aware Unlikelihood Learning Improves Generative Aspect Sentiment Quad Prediction

Uncertainty-Aware Unlikelihood Learning Improves Generative Aspect Sentiment Quad Prediction

URL: http://arxiv.org/abs/2306.00418v2
Date: Sat, 3 Jun 2023 09:48:36 GMT
Title: Uncertainty-Aware Unlikelihood Learning Improves Generative Aspect Sentiment Quad Prediction
Authors: Mengting Hu and Yinhao Bai and Yike Wu and Zhen Zhang and Liqi Zhang and Hang Gao and Shiwan Zhao and Minlie Huang
Abstract summary: We propose a template-agnostic method to control the token-level generation. Specifically, we introduce Monte Carlo dropout to understand the built-in uncertainty of pre-trained language models. We further propose marginalized unlikelihood learning to suppress the uncertainty-aware mistake tokens.
Score: 52.05304897163256
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: Recently, aspect sentiment quad prediction has received widespread attention in the field of aspect-based sentiment analysis. Existing studies extract quadruplets via pre-trained generative language models to paraphrase the original sentence into a templated target sequence. However, previous works only focus on what to generate but ignore what not to generate. We argue that considering the negative samples also leads to potential benefits. In this work, we propose a template-agnostic method to control the token-level generation, which boosts original learning and reduces mistakes simultaneously. Specifically, we introduce Monte Carlo dropout to understand the built-in uncertainty of pre-trained language models, acquiring the noises and errors. We further propose marginalized unlikelihood learning to suppress the uncertainty-aware mistake tokens. Finally, we introduce minimization entropy to balance the effects of marginalized unlikelihood learning. Extensive experiments on four public datasets demonstrate the effectiveness of our approach on various generation templates.

Related papers

Are We Falling in a Middle-Intelligence Trap? An Analysis and Mitigation of the Reversal Curse [73.65112477688353]
Recent studies have highlighted a phenomenon in large language models known as "the reversal curse" We contend that the reversal curse is partially a result of specific model training objectives. We propose a novel training method, BI Casual language modeling Optimization (BICO), designed to mitigate the reversal curse.
arXiv Detail & Related papers (2023-11-13T17:01:12Z)
MiLe Loss: a New Loss for Mitigating the Bias of Learning Difficulties in Generative Language Models [40.992566245706996]
We propose a MiLe Loss function for mitigating the bias of learning difficulties with tokens. We train generative language models at different scales of 468M, 1.2B, and 6.7B parameters. Experiments reveal that models incorporating the proposed MiLe Loss can gain consistent performance improvement on downstream benchmarks.
arXiv Detail & Related papers (2023-10-30T13:33:21Z)
Characterizing Learning Curves During Language Model Pre-Training: Learning, Forgetting, and Stability [28.68721131100346]
We observe that the language models generate short repetitive phrases before learning to generate longer and more coherent text. We quantify the final surprisal, within-run variability, age of acquisition, forgettability, and cross-run variability of learning curves for individual tokens in context. Our work contributes to a better understanding of language model pre-training dynamics and informs the deployment of stable language models in practice.
arXiv Detail & Related papers (2023-08-29T16:24:09Z)
Quark: Controllable Text Generation with Reinforced Unlearning [68.07749519374089]
Large-scale language models often learn behaviors that are misaligned with user expectations. We introduce Quantized Reward Konditioning (Quark), an algorithm for optimizing a reward function that quantifies an (un)wanted property. For unlearning toxicity, negative sentiment, and repetition, our experiments show that Quark outperforms both strong baselines and state-of-the-art reinforcement learning methods.
arXiv Detail & Related papers (2022-05-26T21:11:51Z)
A Simple Contrastive Learning Objective for Alleviating Neural Text Degeneration [56.64703901898937]
We propose a new contrastive token learning objective that inherits the advantages of cross-entropy and unlikelihood training. Comprehensive experiments on language modeling and open-domain dialogue generation tasks show that the proposed contrastive token objective yields less repetitive texts.
arXiv Detail & Related papers (2022-05-05T08:50:50Z)
A Generative Language Model for Few-shot Aspect-Based Sentiment Analysis [90.24921443175514]
We focus on aspect-based sentiment analysis, which involves extracting aspect term, category, and predicting their corresponding polarities. We propose to reformulate the extraction and prediction tasks into the sequence generation task, using a generative language model with unidirectional attention. Our approach outperforms the previous state-of-the-art (based on BERT) on average performance by a large margins in few-shot and full-shot settings.
arXiv Detail & Related papers (2022-04-11T18:31:53Z)
Avoiding Inference Heuristics in Few-shot Prompt-based Finetuning [57.4036085386653]
We show that prompt-based models for sentence pair classification tasks still suffer from a common pitfall of adopting inferences based on lexical overlap. We then show that adding a regularization that preserves pretraining weights is effective in mitigating this destructive tendency of few-shot finetuning.
arXiv Detail & Related papers (2021-09-09T10:10:29Z)
Thought Flow Nets: From Single Predictions to Trains of Model Thought [39.619001911390804]
When humans solve complex problems, they rarely come up with a decision right-away. Instead, they start with an intuitive decision reflecting upon it, spot mistakes, resolve contradictions and jump between different hypotheses.
arXiv Detail & Related papers (2021-07-26T13:56:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.