Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userSample-efficient Linguistic Generalizations through Program Synthesis: Experiments with Phonology Problems
تعميمات لغوية فعالة للعينة من خلال توليف البرامج: تجارب مع مشاكل علم الصوتيات
63
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
النماذج العصبية تتفوق في استخراج الأنماط الإحصائية من كميات كبيرة من البيانات، ولكن الكفاح لتعلم أنماط أو سبب حول اللغة من بعض الأمثلة فقط.في هذه الورقة، نسأل: هل يمكننا أن نتعلم قواعد واضحة تعميم بئر من بعض الأمثلة فقط؟نستكشف هذا السؤال باستخدام تخليق البرنامج.نقوم بتطوير نموذج توليف لتعلم قواعد علم الأصوات كبرامج في لغة خاصة بالمجال.نحن نختبر قدرة نماذجنا على التعميم من بعض الأمثلة التدريبية باستخدام مجموعة بياناتنا الجديدة من مشاكل اللغويات أولمبياد، وهي مجموعة صعبة من المهام التي تتطلب قدرة التفكير اللغوي القوي.بالإضافة إلى كونها كفاءة عالية، فإن نهجنا يولد برامج قابلة للقراءة البشرية، وتسمح بالتحكم في تعميم البرامج المستفادة.
Neural models excel at extracting statistical patterns from large amounts of data, but struggle to learn patterns or reason about language from only a few examples. In this paper, we ask: Can we learn explicit rules that generalize well from only a few examples? We explore this question using program synthesis. We develop a synthesis model to learn phonology rules as programs in a domain-specific language. We test the ability of our models to generalize from few training examples using our new dataset of problems from the Linguistics Olympiad, a challenging set of tasks that require strong linguistic reasoning ability. In addition to being highly sample-efficient, our approach generates human-readable programs, and allows control over the generalizability of the learnt programs.
References used
https://aclanthology.org/
rate research
Read More
Neural dialog models are known to suffer from problems such as generating unsafe and inconsistent responses. Even though these problems are crucial and prevalent, they are mostly manually identified by model designers through interactions. Recently,
some research instructs crowdworkers to goad the bots into triggering such problems. However, humans leverage superficial clues such as hate speech, while leaving systematic problems undercover. In this paper, we propose two methods including reinforcement learning to automatically trigger a dialog model into generating problematic responses. We show the effect of our methods in exposing safety and contradiction issues with state-of-the-art dialog models.
We participated in all tracks of the WMT 2021 efficient machine translation task: single-core CPU, multi-core CPU, and GPU hardware with throughput and latency conditions. Our submissions combine several efficiency strategies: knowledge distillation,
a simpler simple recurrent unit (SSRU) decoder with one or two layers, lexical shortlists, smaller numerical formats, and pruning. For the CPU track, we used quantized 8-bit models. For the GPU track, we experimented with FP16 and 8-bit integers in tensorcores. Some of our submissions optimize for size via 4-bit log quantization and omitting a lexical shortlist. We have extended pruning to more parts of the network, emphasizing component- and block-level pruning that actually improves speed unlike coefficient-wise pruning.
Today, news media organizations regularly engage with readers by enabling them to comment on news articles. This creates the need for comment moderation and removal of disallowed comments -- a time-consuming task often performed by human moderators.
In this paper we approach the problem of automatic news comment moderation as classification of comments into blocked and not blocked categories. We construct a novel dataset of annotated English comments, experiment with cross-lingual transfer of comment labels and evaluate several machine learning models on datasets of Croatian and Estonian news comments. Team name: SuperAdmin; Challenge: Detection of blocked comments; Tools/models: CroSloEn BERT, FinEst BERT, 24Sata comment dataset, Ekspress comment dataset.
This work investigates the value of augmenting recurrent neural networks with feature engineering for the Second Nuanced Arabic Dialect Identification (NADI) Subtask 1.2: Country-level DA identification. We compare the performance of a simple word-le
vel LSTM using pretrained embeddings with one enhanced using feature embeddings for engineered linguistic features. Our results show that the addition of explicit features to the LSTM is detrimental to performance. We attribute this performance loss to the bivalency of some linguistic items in some text, ubiquity of topics, and participant mobility.
People convey their intention and attitude through linguistic styles of the text that they write. In this study, we investigate lexicon usages across styles throughout two lenses: human perception and machine word importance, since words differ in th
e strength of the stylistic cues that they provide. To collect labels of human perception, we curate a new dataset, Hummingbird, on top of benchmarking style datasets. We have crowd workers highlight the representative words in the text that makes them think the text has the following styles: politeness, sentiment, offensiveness, and five emotion types. We then compare these human word labels with word importance derived from a popular fine-tuned style classifier like BERT. Our results show that the BERT often finds content words not relevant to the target style as important words used in style prediction, but humans do not perceive the same way even though for some styles (e.g., positive sentiment and joy) human- and machine-identified words share significant overlap for some styles.
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
