Arithmetic-Based Pretraining Improving Numeracy of Pretrained Language Models (2023.starsem-1)
Copied to clipboard
| Challenge: | Recent work suggests that pretrained language models perform below their capabilities when applied out-of-the-box on tasks that require understanding and working with numbers. |
| Approach: | They propose an extended pretraining approach that addresses both in one extended step . they propose a novel extended pre training objective called Inferable Number Prediction Task to improve numeracy. |
| Outcome: | The proposed approach improves reading comprehension and inference-on-tables tasks without architectural changes or pretraining from scratch. |
Similar Papers
Can Sequence-to-Sequence Transformers Naturally Understand Sequential Instructions? (2023.starsem-1)
Copied to clipboard
| Challenge: | Using a limited annotation budget, we can greatly improve the performance on intermediate steps with a drop in final-step performance. |
| Approach: | They propose to use a pre-supervised sequence-to-sequence transformer to provide training signals on intermediate steps with zero gold supervision instead of only final-step supervision to improve performance. |
| Outcome: | The proposed model significantly improves on intermediate steps with a drop in final-step performance on one subtask, but also shows decreased performance on another subtask. |
Dyna-bAbI: unlocking bAbI’s potential with dynamic synthetic benchmarking (2022.starsem-1)
Copied to clipboard
Ronen Tamari, Kyle Richardson, Noam Kahlon, Aviad Sar-shalom, Nelson F. Liu, Reut Tsarfaty, Dafna Shahaf
| Challenge: | Controlled synthetic tasks are an important resource for diagnosing model behavior. |
| Approach: | They propose a framework that provides fine-grained control over task generation in bAbI. |
| Outcome: | The proposed framework provides fine-grained control over task generation in the bAbI benchmark. |
Teach the Rules, Provide the Facts: Targeted Relational-knowledge Enhancement for Textual Inference (2021.starsem-1)
Copied to clipboard
| Challenge: | InferBERT is a method to enhance transformer-based inference models with relevant relational knowledge. |
| Approach: | They propose to enhance transformer-based inference models with relevant relational knowledge by injecting relevant facts at test time into the model. |
| Outcome: | The proposed method outperforms existing models on the challenge datasets while outperforming existing models. |
Compositional Structured Explanation Generation with Dynamic Modularized Reasoning (2024.starsem-1)
Copied to clipboard
| Challenge: | Large-scale language models have shown remarkable performance on reasoning tasks such as reading comprehension, natural language inference, story generation, etc. |
| Approach: | They propose a compositional structured explanation generation task to test a model's ability to generalize from generating entailment trees to more steps, focusing on the length and shapes of engorgement trees. |
| Outcome: | The proposed model shows competitive compositional generalization abilities in a generation setting. |
Overcoming Poor Word Embeddings with Word Definitions (2021.starsem-1)
Copied to clipboard
| Challenge: | Modern natural language understanding models depend on pretrained word embeddings, but applications may need to reason about words that were never or rarely seen during pretraining. |
| Approach: | They propose a method to improve a model's ability to learn to use definitions in natural text to overcome this handicap. |
| Outcome: | The proposed model learns to use definitions in natural text to overcome this handicap. |
Empirical Sufficiency Lower Bounds for Language Modeling with Locally-Bootstrapped Semantic Structures (2023.starsem-1)
Copied to clipboard
| Challenge: | a recent attempt at language modeling with predicted semantic structure failed to establish empirical lower bounds on what could have made the attempt successful. |
| Approach: | They propose a concise binary vector representation of semantic structure at the lexical level and evaluate how good an incremental tagger needs to be to achieve better-than-baseline performance. |
| Outcome: | The proposed model can achieve better-than-baseline performance without losing its main advantages and lower bounds on prediction quality can't be established via a single score alone. |
Speedy Gonzales: A Collection of Fast Task-Specific Models for Spanish (2024.starsem-1)
Copied to clipboard
| Challenge: | Large language models (LLMs) are a common and successful approach to language and retrieval tasks. |
| Approach: | They evaluate the available large language models in Spanish and then use knowledge distillation to refine and distill them. |
| Outcome: | The proposed models are fine-tuned and distilled on knowledge distillation and are available on huggingface.co/dccuchile. |
One Semantic Parser to Parse Them All: Sequence to Sequence Multi-Task Learning on Semantic Parsing Datasets (2021.starsem-1)
Copied to clipboard
| Challenge: | Existing semantic parsing datasets lack a single standard for meaning representations . lack of a standard led to the creation of plethora of datasets requiring expert annotators . |
| Approach: | They propose to use multi-task learning to unify different datasets and train a single model for them. |
| Outcome: | The proposed architectures yield better parsing accuracies and composition generalization than single-task models. |
Lexical Substitution as Causal Language Modeling (2024.starsem-1)
Copied to clipboard
| Challenge: | Existing methods for lexical substitution task lacks autoregressive decoding capabilities. |
| Approach: | They propose a framework that uses causal language modeling (CLM) for lexical substitution task. |
| Outcome: | The proposed system outperforms GeneSis, the best previously published supervised LST method. |
DeepA2: A Modular Framework for Deep Argument Analysis with Pretrained Neural Text2Text Language Models (2022.starsem-1)
Copied to clipboard
| Challenge: | ArgumentAnalyst is a multi-dimensional, modular framework for performing deep argument analysis using existing pre-trained language models (PTLMs). |
| Approach: | They propose a multi-dimensional, modular framework for performing deep argument analysis using current pre-trained language models (PTLMs) ArgumentAnalyst reconstructs argumentative texts as valid arguments by inserting missing premises and conclusions, formalizing inferences, and coherently linking the reconstruction to the source text. |
| Outcome: | The proposed framework can replicate established heuristics, cope with plurality of correct solutions, and exploit higher-order evidence. |