Related papers: Revisiting the Roles of "Text" in Text Games

Revisiting the Roles of "Text" in Text Games

URL: http://arxiv.org/abs/2210.08384v1
Date: Sat, 15 Oct 2022 21:52:39 GMT
Title: Revisiting the Roles of "Text" in Text Games
Authors: Yi Gu, Shunyu Yao, Chuang Gan, Joshua B. Tenenbaum, Mo Yu
Abstract summary: This paper investigates the roles of text in the face of different reinforcement learning challenges. We propose a simple scheme to extract relevant contextual information into an approximate state hash. Such a lightweight plug-in achieves competitive performance with state-of-the-art text agents.
Score: 102.22750109468652
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: Text games present opportunities for natural language understanding (NLU) methods to tackle reinforcement learning (RL) challenges. However, recent work has questioned the necessity of NLU by showing random text hashes could perform decently. In this paper, we pursue a fine-grained investigation into the roles of text in the face of different RL challenges, and reconcile that semantic and non-semantic language representations could be complementary rather than contrasting. Concretely, we propose a simple scheme to extract relevant contextual information into an approximate state hash as extra input for an RNN-based text agent. Such a lightweight plug-in achieves competitive performance with state-of-the-art text agents using advanced NLU techniques such as knowledge graph and passage retrieval, suggesting non-NLU methods might suffice to tackle the challenge of partial observability. However, if we remove RNN encoders and use approximate or even ground-truth state hash alone, the model performs miserably, which confirms the importance of semantic function approximation to tackle the challenge of combinatorially large observation and action spaces. Our findings and analysis provide new insights for designing better text game task setups and agents.

Related papers

EXPLORER: Exploration-guided Reasoning for Textual Reinforcement Learning [23.83162741035859]
We present EXPLORER, which is an exploration-guided reasoning agent for textual reinforcement learning. Our experiments show that EXPLORER outperforms the baseline agents on Text-World cooking (TW-Cooking) and Text-World Commonsense (TWC) games.
arXiv Detail & Related papers (2024-03-15T21:22:37Z)
Not Enough Labeled Data? Just Add Semantics: A Data-Efficient Method for Inferring Online Health Texts [0.0]
We employ Abstract Representation (AMR) graphs as a means to model low-resource Health NLP tasks. AMRs are well suited to model online health texts as they represent multi-sentence inputs, abstract away from complex terminology, and model long-distance relationships. Our experiments show that we can improve performance on 6 low-resource health NLP tasks by augmenting text embeddings with semantic graph embeddings.
arXiv Detail & Related papers (2023-09-18T15:37:30Z)
Towards General Visual-Linguistic Face Forgery Detection [95.73987327101143]
Deepfakes are realistic face manipulations that can pose serious threats to security, privacy, and trust. Existing methods mostly treat this task as binary classification, which uses digital labels or mask signals to train the detection model. We propose a novel paradigm named Visual-Linguistic Face Forgery Detection(VLFFD), which uses fine-grained sentence-level prompts as the annotation.
arXiv Detail & Related papers (2023-07-31T10:22:33Z)
Learning Symbolic Rules over Abstract Meaning Representations for Textual Reinforcement Learning [63.148199057487226]
We propose a modular, NEuroSymbolic Textual Agent (NESTA) that combines a generic semantic generalization with a rule induction system to learn interpretable rules as policies. Our experiments show that the proposed NESTA method outperforms deep reinforcement learning-based techniques by achieving better to unseen test games and learning from fewer training interactions.
arXiv Detail & Related papers (2023-07-05T23:21:05Z)
TextFormer: A Query-based End-to-End Text Spotter with Mixed Supervision [61.186488081379]
We propose TextFormer, a query-based end-to-end text spotter with Transformer architecture. TextFormer builds upon an image encoder and a text decoder to learn a joint semantic understanding for multi-task modeling. It allows for mutual training and optimization of classification, segmentation, and recognition branches, resulting in deeper feature sharing.
arXiv Detail & Related papers (2023-06-06T03:37:41Z)
Textual Enhanced Contrastive Learning for Solving Math Word Problems [23.196339273292246]
We propose a Textual Enhanced Contrastive Learning framework, which enforces the models to distinguish semantically similar examples. We adopt a self-supervised manner strategy to enrich examples with subtle textual variance. Experimental results show that our method achieves state-of-the-art on both widely used benchmark datasets and also exquisitely designed challenge datasets in English and Chinese.
arXiv Detail & Related papers (2022-11-29T08:44:09Z)
Interactive Fiction Game Playing as Multi-Paragraph Reading Comprehension with Reinforcement Learning [94.50608198582636]
Interactive Fiction (IF) games with real human-written natural language texts provide a new natural evaluation for language understanding techniques. We take a novel perspective of IF game solving and re-formulate it as Multi-Passage Reading (MPRC) tasks.
arXiv Detail & Related papers (2020-10-05T23:09:20Z)
Towards Accurate Scene Text Recognition with Semantic Reasoning Networks [52.86058031919856]
We propose a novel end-to-end trainable framework named semantic reasoning network (SRN) for accurate scene text recognition. GSRM is introduced to capture global semantic context through multi-way parallel transmission. Results on 7 public benchmarks, including regular text, irregular text and non-Latin long text, verify the effectiveness and robustness of the proposed method.
arXiv Detail & Related papers (2020-03-27T09:19:25Z)

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