Related papers: PatentTransformer-2: Controlling Patent Text Gener…
Retrieval-Augmented Generation systems depend on retrieving semantically relevant document chunks to support accurate, grounded outputs from large language models. In structured and repetitive corpora such as regulatory filings, chunk…
LLMs are becoming increasingly capable and widespread. Consequently, the potential and reality of their misuse is also growing. In this work, we address the problem of detecting LLM-generated text that is not explicitly declared as such. We…
We propose a novel domain-specific generative pre-training (DS-GPT) method for text generation and apply it to the product titleand review summarization problems on E-commerce mobile display.First, we adopt a decoder-only transformer…
Controllable text generation systems often leverage control codes to direct various properties of the output like style and length. Inspired by recent work on causal inference for NLP, this paper reveals a previously overlooked flaw in…
Transformer-based models have achieved strong performance in remote sensing image captioning by capturing long-range dependencies and contextual information. However, their practical deployment is hindered by high computational costs,…
A patent must be deemed novel and non-obvious in order to be granted by the US Patent Office (USPTO). If it is not, a US patent examiner will cite the prior work, or prior art, that invalidates the novelty and issue a non-final rejection.…
Professional translators often dictate their translations orally and have them typed afterwards. The TransTalk project aims at automating the second part of this process. Its originality as a dictation system lies in the fact that both the…
We introduce Transformer Grammars (TGs), a novel class of Transformer language models that combine (i) the expressive power, scalability, and strong performance of Transformers and (ii) recursive syntactic compositions, which here are…
We introduce _transparent documents_, interactive web-based scholarly articles which allow readers to explore the relationship to the underlying data by hovering over fragments of text, and present an LLM-based tool for authoring…
Patent data have long been used for engineering design research because of its large and expanding size, and widely varying massive amount of design information contained in patents. Recent advances in artificial intelligence and data…
Machine-generated citation sentences can aid automated scientific literature review and assist article writing. Current methods in generating citation text were limited to single citation generation using the citing document and a cited…
Collecting robotic manipulation data is expensive, making it impractical to acquire demonstrations for the combinatorially large space of tasks that arise in multi-object, multi-robot, and multi-environment settings. While recent generative…
Text style transfer is the task that generates a sentence by preserving the content of the input sentence and transferring the style. Most existing studies are progressing on non-parallel datasets because parallel datasets are limited and…
This paper presents Patent-CR, the first dataset created for the patent claim revision task in English. It includes both initial patent applications rejected by patent examiners and the final granted versions. Unlike normal text revision…
We study the patent phrase similarity inference task, which measures the semantic similarity between two patent phrases. As patent documents employ legal and highly technical language, existing semantic textual similarity methods that use…
This paper presents a tree-to-tree transduction method for sentence compression. Our model is based on synchronous tree substitution grammar, a formalism that allows local distortion of the tree topology and can thus naturally capture…
Short text classification is a crucial and challenging aspect of Natural Language Processing. For this reason, there are numerous highly specialized short text classifiers. However, in recent short text research, State of the Art (SOTA)…
This paper proposes a novel neural model for the understudied task of generating text from keywords. The model takes as input a set of un-ordered keywords, and part-of-speech (POS) based template instructions. This makes it ideal for…
When directly using existing text generation datasets for controllable generation, we are facing the problem of not having the domain knowledge and thus the aspects that could be controlled are limited. A typical example is when using…
The growing developments in general semantic networks, knowledge graphs and ontology databases have motivated us to build a large-scale comprehensive semantic network of technology-related data for engineering knowledge discovery,…