Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userAnalysis of Language Change in Collaborative Instruction Following
تحليل تغيير اللغة في التعليم التعاوني التالي
137
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
نقوم بتحليل تغيير اللغة بمرور الوقت في مهمة تعليمية تعاونية وموجهة نحو تحقيق الأهداف، حيث تكثف المرافق تعظيم المشاركين في الاتفاقيات وزيادة خبراتهم.درس العمل المسبق مثل هذه السيناريوهات في الغالب في سياق الألعاب المرجعية، ووجدت باستمرار أن تعقيد اللغة يتم تقليلها على طول أبعاد متعددة، مثل طول الكلام، مع تشكيل الاتفاقيات.على النقيض من ذلك، نجد أنه نظرا للقدرة على زيادة المرافق التعليمية، يقوم المدربون بزيادة تعقيد اللغة على طول هذه الأبعاد التي تمت دراستها سابقا للتعاون بشكل أفضل مع أتباع تعليمات ماهرة بشكل متزايد.
We analyze language change over time in a collaborative, goal-oriented instructional task, where utility-maximizing participants form conventions and increase their expertise. Prior work studied such scenarios mostly in the context of reference games, and consistently found that language complexity is reduced along multiple dimensions, such as utterance length, as conventions are formed. In contrast, we find that, given the ability to increase instruction utility, instructors increase language complexity along these previously studied dimensions to better collaborate with increasingly skilled instruction followers.
References used
https://aclanthology.org/
rate research
Read More
Understanding and executing natural language instructions in a grounded domain is one of the hallmarks of artificial intelligence. In this paper, we focus on instruction understanding in the blocks world domain and investigate the language understand
ing abilities of two top-performing systems for the task. We aim to understand if the test performance of these models indicates an understanding of the spatial domain and of the natural language instructions relative to it, or whether they merely over-fit spurious signals in the dataset. We formulate a set of expectations one might have from an instruction following model and concretely characterize the different dimensions of robustness such a model should possess. Despite decent test performance, we find that state-of-the-art models fall short of these expectations and are extremely brittle. We then propose a learning strategy that involves data augmentation and show through extensive experiments that the proposed learning strategy yields models that are competitive on the original test set while satisfying our expectations much better.
Abstract We study continual learning for natural language instruction generation, by observing human users' instruction execution. We focus on a collaborative scenario, where the system both acts and delegates tasks to human users using natural langu
age. We compare user execution of generated instructions to the original system intent as an indication to the system's success communicating its intent. We show how to use this signal to improve the system's ability to generate instructions via contextual bandit learning. In interaction with real users, our system demonstrates dramatic improvements in its ability to generate language over time.
Standard architectures used in instruction following often struggle on novel compositions of subgoals (e.g. navigating to landmarks or picking up objects) observed during training. We propose a modular architecture for following natural language inst
ructions that describe sequences of diverse subgoals. In our approach, subgoal modules each carry out natural language instructions for a specific subgoal type. A sequence of modules to execute is chosen by learning to segment the instructions and predicting a subgoal type for each segment. When compared to standard, non-modular sequence-to-sequence approaches on ALFRED, a challenging instruction following benchmark, we find that modularization improves generalization to novel subgoal compositions, as well as to environments unseen in training.
Transformer architecture has become ubiquitous in the natural language processing field. To interpret the Transformer-based models, their attention patterns have been extensively analyzed. However, the Transformer architecture is not only composed of
the multi-head attention; other components can also contribute to Transformers' progressive performance. In this study, we extended the scope of the analysis of Transformers from solely the attention patterns to the whole attention block, i.e., multi-head attention, residual connection, and layer normalization. Our analysis of Transformer-based masked language models shows that the token-to-token interaction performed via attention has less impact on the intermediate representations than previously assumed. These results provide new intuitive explanations of existing reports; for example, discarding the learned attention patterns tends not to adversely affect the performance. The codes of our experiments are publicly available.
The span-based model enjoys great popularity in recent works of sequence segmentation. However, each of these methods suffers from its own defects, such as invalid predictions. In this work, we introduce a unified span-based model, lexical unit analy
sis (LUA), that addresses all these matters. Segmenting a lexical unit sequence involves two steps. Firstly, we embed every span by using the representations from a pretraining language model. Secondly, we define a score for every segmentation candidate and apply dynamic programming (DP) to extract the candidate with the maximum score. We have conducted extensive experiments on 3 tasks, (e.g., syntactic chunking), across 7 datasets. LUA has established new state-of-the-art performances on 6 of them. We have achieved even better results through incorporating label correlations.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
