Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new user``I'm Not Mad'': Commonsense Implications of Negation and Contradiction
"أنا لست مجنونا": آثار المنطقية عن النفي والتناقض
44
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
إن الاستدلال اللغوي الطبيعي يتطلب منطق حول التناقضات واللبنات وآثارها المنطقية. بالنظر إلى فرضية بسيطة (على سبيل المثال، أنا مجنون منك ")، يمكن للبشر سبب ظلال متفاوتة من البيانات المتناقضة التي تتراوح من نفيها واضحة (أنا لست غاضبا منك") لتناقضات المنطقية (أنا سعيد ''). علاوة على ذلك، تحول هذه البيانات المنفدة أو المتناقضة الآثار المترتبة على الفرضية الأصلية بطرق مثيرة للاهتمام وغير خيالية. على سبيل المثال، بينما أنا مجنون "يعني أنني غير راض عن شيء ما"، ينفي الفرضية لا ينفي بالضرورة آثار المنطقية المقابلة. في هذه الورقة، نقدم أول دراسة شاملة تركز على آثار المنزول على البيانات المنفذة والتناقضات. نقدم أنيون، الرسم البياني المعرفة بالمنشط الجديد مع 624 ألف إذا كان قواعد التركيز على الأحداث الناجمة والتناقض. ثم نقدم نماذج الاستدلال الإنتاجية والتمييزية المشتركة لهذا المورد الجديد، مما يوفر رؤى تجريبية رواية حول كيفية إعادة النفايات المنطقية والتناقضات المنطقية من الآثار المترتبة على المباني الأصلية.
Natural language inference requires reasoning about contradictions, negations, and their commonsense implications. Given a simple premise (e.g., I'm mad at you''), humans can reason about the varying shades of contradictory statements ranging from straightforward negations (I'm not mad at you'') to commonsense contradictions (I'm happy''). Moreover, these negated or contradictory statements shift the commonsense implications of the original premise in interesting and nontrivial ways. For example, while I'm mad'' implies I'm unhappy about something,'' negating the premise does not necessarily negate the corresponding commonsense implications. In this paper, we present the first comprehensive study focusing on commonsense implications of negated statements and contradictions. We introduce ANION, a new commonsense knowledge graph with 624K if-then rules focusing on negated and contradictory events. We then present joint generative and discriminative inference models for this new resource, providing novel empirical insights on how logical negations and commonsense contradictions reshape the commonsense implications of their original premises.
References used
https://aclanthology.org/
rate research
Read More
This paper introduces NorecNeg -- the first annotated dataset of negation for Norwegian. Negation cues and their in-sentence scopes have been annotated across more than 11K sentences spanning more than 400 documents for a subset of the Norwegian Revi
ew Corpus (NoReC). In addition to providing in-depth discussion of the annotation guidelines, we also present a first set of benchmark results based on a graph-parsing approach.
Sarcasm detection is important for several NLP tasks such as sentiment identification in product reviews, user feedback, and online forums. It is a challenging task requiring a deep understanding of language, context, and world knowledge. In this pap
er, we investigate whether incorporating commonsense knowledge helps in sarcasm detection. For this, we incorporate commonsense knowledge into the prediction process using a graph convolution network with pre-trained language model embeddings as input. Our experiments with three sarcasm detection datasets indicate that the approach does not outperform the baseline model. We perform an exhaustive set of experiments to analyze where commonsense support adds value and where it hurts classification. Our implementation is publicly available at: https://github.com/brcsomnath/commonsense-sarcasm.
Negation scope resolution is key to high-quality information extraction from clinical texts, but so far, efforts to make encoders used for information extraction negation-aware have been limited to English. We present a universal approach to multilin
gual negation scope resolution, that overcomes the lack of training data by relying on disparate resources in different languages and domains. We evaluate two approaches to learn from these resources, training on combined data and training in a multi-task learning setup. Our experiments show that zero-shot scope resolution in clinical text is possible, and that combining available resources improves performance in most cases.
In deployment, systems that use speech as input must make use of automated transcriptions. Yet, typically when these systems are evaluated, gold transcriptions are assumed. We explicitly examine the impact of transcription errors on the downstream pe
rformance of a multi-modal system on three related tasks from three datasets: emotion, sarcasm, and personality detection. We include three separate transcription tools and show that while all automated transcriptions propagate errors that substantially impact downstream performance, the open-source tools fair worse than the paid tool, though not always straightforwardly, and word error rates do not correlate well with downstream performance. We further find that the inclusion of audio features partially mitigates transcription errors, but that a naive usage of a multi-task setup does not.
Common sense is an integral part of human cognition which allows us to make sound decisions, communicate effectively with others and interpret situations and utterances. Endowing AI systems with commonsense knowledge capabilities will help us get clo
ser to creating systems that exhibit human intelligence. Recent efforts in Natural Language Generation (NLG) have focused on incorporating commonsense knowledge through large-scale pre-trained language models or by incorporating external knowledge bases. Such systems exhibit reasoning capabilities without common sense being explicitly encoded in the training set. These systems require careful evaluation, as they incorporate additional resources during training which adds additional sources of errors. Additionally, human evaluation of such systems can have significant variation, making it impossible to compare different systems and define baselines. This paper aims to demystify human evaluations of commonsense-enhanced NLG systems by proposing the Commonsense Evaluation Card (CEC), a set of recommendations for evaluation reporting of commonsense-enhanced NLG systems, underpinned by an extensive analysis of human evaluations reported in the recent literature.
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
