Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userEffect Generation Based on Causal Reasoning
تأثير الجيل بناء على التفكير السببية
283
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
يهدف السبب السببي إلى التنبؤ بالسيناريوهات المستقبلية التي قد يكون سببها الإجراءات الملحوظة.ومع ذلك، فإن أساليب المنطق السببية الموجودة تتعامل مع الضغط على مستوى الكلمة.في هذه الورقة، نقترح طريقة التفكير السببية السببية على مستوى الحدث وإظهار استخدامها في مهمة توليد التأثير.على وجه الخصوص، نقوم بتكييف أزواج الأحداث التي تمت ملاحظتها في السبب في شبكة سببية حدث، والتي تصف التبعيات السببية.بالنظر إلى جملة مدخلات، يتم استرداد مجموعة فرعية سببية من شبكة السببية الحدث ويتم ترميزها مع آلية اهتمامات الرسم البياني، من أجل دعم التفكير الأفضل للآثار المحتملة.ثم يتم تحديد حدث التأثير الأكثر احتمالا من الفحص الفرعي السببي ويستخدم كإرشادات لتوليد جملة تأثير.تظهر التجارب أن طريقتنا تولد جمل أكثر معقولة من مختلف المنافسين المصممين بشكل جيد.
Causal reasoning aims to predict the future scenarios that may be caused by the observed actions. However, existing causal reasoning methods deal with causalities on the word level. In this paper, we propose a novel event-level causal reasoning method and demonstrate its use in the task of effect generation. In particular, we structuralize the observed cause-effect event pairs into an event causality network, which describes causality dependencies. Given an input cause sentence, a causal subgraph is retrieved from the event causality network and is encoded with the graph attention mechanism, in order to support better reasoning of the potential effects. The most probable effect event is then selected from the causal subgraph and is used as guidance to generate an effect sentence. Experiments show that our method generates more reasonable effect sentences than various well-designed competitors.
References used
https://aclanthology.org/
rate research
Read More
We perform neural machine translation of sentence fragments in order to create large amounts of training data for English grammatical error correction. Our method aims at simulating mistakes made by second language learners, and produces a wider rang
e of non-native style language in comparison to a state-of-the-art baseline model. We carry out quantitative and qualitative evaluation. Our method is shown to outperform the baseline on data with a high proportion of errors.
We consider the problem of using observational data to estimate the causal effects of linguistic properties. For example, does writing a complaint politely lead to a faster response time? How much will a positive product review increase sales? This p
aper addresses two technical challenges related to the problem before developing a practical method. First, we formalize the causal quantity of interest as the effect of a writer's intent, and establish the assumptions necessary to identify this from observational data. Second, in practice, we only have access to noisy proxies for the linguistic properties of interest---e.g., predictions from classifiers and lexicons. We propose an estimator for this setting and prove that its bias is bounded when we perform an adjustment for the text. Based on these results, we introduce TextCause, an algorithm for estimating causal effects of linguistic properties. The method leverages (1) distant supervision to improve the quality of noisy proxies, and (2) a pre-trained language model (BERT) to adjust for the text. We show that the proposed method outperforms related approaches when estimating the effect of Amazon review sentiment on semi-simulated sales figures. Finally, we present an applied case study investigating the effects of complaint politeness on bureaucratic response times.
Abstract Recent improvements in the predictive quality of natural language processing systems are often dependent on a substantial increase in the number of model parameters. This has led to various attempts of compressing such models, but existing m
ethods have not considered the differences in the predictive power of various model components or in the generalizability of the compressed models. To understand the connection between model compression and out-of-distribution generalization, we define the task of compressing language representation models such that they perform best in a domain adaptation setting. We choose to address this problem from a causal perspective, attempting to estimate the average treatment effect (ATE) of a model component, such as a single layer, on the model's predictions. Our proposed ATE-guided Model Compression scheme (AMoC), generates many model candidates, differing by the model components that were removed. Then, we select the best candidate through a stepwise regression model that utilizes the ATE to predict the expected performance on the target domain. AMoC outperforms strong baselines on dozens of domain pairs across three text classification and sequence tagging tasks.1
Reference-based automatic evaluation metrics are notoriously limited for NLG due to their inability to fully capture the range of possible outputs. We examine a referenceless alternative: evaluating the adequacy of English sentences generated from Ab
stract Meaning Representation (AMR) graphs by parsing into AMR and comparing the parse directly to the input. We find that the errors introduced by automatic AMR parsing substantially limit the effectiveness of this approach, but a manual editing study indicates that as parsing improves, parsing-based evaluation has the potential to outperform most reference-based metrics.
This paper presents a global summarization method for live sport commentaries for which we have a human-written summary available. This method is based on a neural generative summarizer. The amount of data available for training is limited compared t
o corpora commonly used by neural summarizers. We propose to help the summarizer to learn from a limited amount of data by limiting the entropy of the input texts. This step is performed by a classification into categories derived by a detailed analysis of the human-written summaries. We show that the filtering helps the summarization system to overcome the lack of resources. However, several improving points have emerged from this preliminary study, that we discuss and plan to implement in future work.
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
